< Prev | Home | Model | Random | Next >

Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 331 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')



Text #0

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.4825. Min Act: -0.1700

Data Index: 788447 (C4 (Web Text))

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.4338. Min Act: -0.1700

Data Index: 1054395 (C4 (Web Text))

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.4501. Min Act: -0.1700

Data Index: 377705 (C4 (Web Text))

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.4501. Min Act: -0.1700

Data Index: 1235220 (C4 (Web Text))

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.4338. Min Act: -0.1700

Data Index: 1344368 (C4 (Web Text))

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.4175. Min Act: -0.1700

Data Index: 101554 (C4 (Web Text))

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.4175. Min Act: -0.1700

Data Index: 1322896 (C4 (Web Text))

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.4175. Min Act: -0.1700

Data Index: 890828 (C4 (Web Text))

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.4012. Min Act: -0.1700

Data Index: 970891 (C4 (Web Text))

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3849. Min Act: -0.1700

Data Index: 436671 (C4 (Web Text))

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3686. Min Act: -0.1700

Data Index: 1615960 (Python Code)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3522. Min Act: -0.1700

Data Index: 1430505 (Python Code)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3522. Min Act: -0.1700

Data Index: 274884 (C4 (Web Text))

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3849. Min Act: -0.1700

Data Index: 1147396 (C4 (Web Text))

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3686. Min Act: -0.1700

Data Index: 1002291 (C4 (Web Text))

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3522. Min Act: -0.1700

Data Index: 880705 (C4 (Web Text))

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3686. Min Act: -0.1700

Data Index: 266745 (C4 (Web Text))

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3686. Min Act: -0.1700

Data Index: 997436 (C4 (Web Text))

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3522. Min Act: -0.1700

Data Index: 1152189 (C4 (Web Text))

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.4825. Min Range: -2.4825

Max Act: 2.3522. Min Act: -0.1700

Data Index: 130388 (C4 (Web Text))

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #19