< Prev | Home | Model | Random | Next >

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

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

Neuron 870 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: 3.1408. Min Range: -3.1408

Max Act: 3.1408. Min Act: -0.1700

Data Index: 1328056 (C4 (Web Text))

Max Activating Token Index: 409

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9988. Min Act: -0.1700

Data Index: 1540335 (Python Code)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9671. Min Act: -0.1700

Data Index: 1249148 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9513. Min Act: -0.1699

Data Index: 1545974 (Python Code)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9355. Min Act: -0.1700

Data Index: 1501091 (Python Code)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9196. Min Act: -0.1700

Data Index: 1608430 (Python Code)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9513. Min Act: -0.1700

Data Index: 1578179 (Python Code)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9355. Min Act: -0.1700

Data Index: 1600093 (Python Code)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9196. Min Act: -0.1700

Data Index: 1411987 (Python Code)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9038. Min Act: -0.1700

Data Index: 1495061 (Python Code)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9196. Min Act: -0.1700

Data Index: 1499251 (Python Code)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.8879. Min Act: -0.1700

Data Index: 1609631 (Python Code)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.9038. Min Act: -0.1700

Data Index: 1436195 (Python Code)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.8879. Min Act: -0.1700

Data Index: 1435968 (Python Code)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.8879. Min Act: -0.1700

Data Index: 1360045 (Python Code)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.8879. Min Act: -0.1700

Data Index: 1573385 (Python Code)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.8879. Min Act: -0.1700

Data Index: 1467963 (Python Code)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.8720. Min Act: -0.1700

Data Index: 1597138 (Python Code)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.8720. Min Act: -0.1700

Data Index: 1563480 (Python Code)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1408. Min Range: -3.1408

Max Act: 2.8720. Min Act: -0.1700

Data Index: 1477790 (Python Code)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #19