< Prev | Home | Model | Random | Next >

Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 486 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')



Text #0

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.5680. Min Act: -0.1700

Data Index: 910859 (C4 (Web Text))

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.5357. Min Act: -0.1700

Data Index: 1538966 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.5196. Min Act: -0.1700

Data Index: 1532996 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.5034. Min Act: -0.1700

Data Index: 658660 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4872. Min Act: -0.1700

Data Index: 948964 (C4 (Web Text))

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4872. Min Act: -0.1700

Data Index: 1076645 (C4 (Web Text))

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4872. Min Act: -0.1700

Data Index: 1379469 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.5034. Min Act: -0.1700

Data Index: 586269 (C4 (Web Text))

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4709. Min Act: -0.1700

Data Index: 280044 (C4 (Web Text))

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4547. Min Act: -0.1700

Data Index: 39662 (C4 (Web Text))

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4709. Min Act: -0.1700

Data Index: 653116 (C4 (Web Text))

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4547. Min Act: -0.1700

Data Index: 760407 (C4 (Web Text))

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4709. Min Act: -0.1700

Data Index: 951114 (C4 (Web Text))

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4709. Min Act: -0.1700

Data Index: 59493 (C4 (Web Text))

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4709. Min Act: -0.1700

Data Index: 195636 (C4 (Web Text))

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4709. Min Act: -0.1700

Data Index: 458329 (C4 (Web Text))

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4709. Min Act: -0.1700

Data Index: 866978 (C4 (Web Text))

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4547. Min Act: -0.1700

Data Index: 105250 (C4 (Web Text))

Max Activating Token Index: 90

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4709. Min Act: -0.1700

Data Index: 851091 (C4 (Web Text))

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5680. Min Range: -2.5680

Max Act: 2.4547. Min Act: -0.1700

Data Index: 832523 (C4 (Web Text))

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #19