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

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

Neuron 1979 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0283. Min Range: -5.0283

Max Act: 5.0283. Min Act: -0.1700

Data Index: 12658 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.9971. Min Act: -0.1700

Data Index: 216189 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 5.0283. Min Range: -5.0283

Max Act: 5.0283. Min Act: -0.1700

Data Index: 540026 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.9971. Min Act: -0.1700

Data Index: 798015 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8721. Min Act: -0.1700

Data Index: 1483304 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.9033. Min Act: -0.1700

Data Index: 1547309 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8408. Min Act: -0.1700

Data Index: 1589892 (Python Code)

Max Activating Token Index: 51

Text #7

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8721. Min Act: -0.1700

Data Index: 1374036 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.9033. Min Act: -0.1700

Data Index: 101405 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8408. Min Act: -0.1700

Data Index: 1656379 (Python Code)

Max Activating Token Index: 51

Text #10

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8096. Min Act: -0.1699

Data Index: 1432021 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8408. Min Act: -0.1700

Data Index: 1523873 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8721. Min Act: -0.1700

Data Index: 991871 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8096. Min Act: -0.1700

Data Index: 1561273 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8721. Min Act: -0.1700

Data Index: 1404184 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8408. Min Act: -0.1700

Data Index: 1611452 (Python Code)

Max Activating Token Index: 230

Text #16

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8408. Min Act: -0.1700

Data Index: 1414289 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8408. Min Act: -0.1700

Data Index: 1640598 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.7783. Min Act: -0.1700

Data Index: 1437146 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 5.0283. Min Range: -5.0283

Max Act: 4.8721. Min Act: -0.1700

Data Index: 1523762 (Python Code)

Max Activating Token Index: 72