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

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

Neuron 1096 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: 5.1164. Min Range: -5.1164

Max Act: 5.1164. Min Act: -0.1700

Data Index: 797023 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 5.1164. Min Range: -5.1164

Max Act: 5.0227. Min Act: -0.1700

Data Index: 1066899 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 5.1164. Min Range: -5.1164

Max Act: 5.0227. Min Act: -0.1700

Data Index: 1277287 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.8977. Min Act: -0.1700

Data Index: 1300583 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.8664. Min Act: -0.1700

Data Index: 1241830 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.8664. Min Act: -0.1700

Data Index: 356158 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.8039. Min Act: -0.1700

Data Index: 127556 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.7727. Min Act: -0.1700

Data Index: 1272150 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.7414. Min Act: -0.1700

Data Index: 753948 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.7727. Min Act: -0.1700

Data Index: 1188556 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.7414. Min Act: -0.1700

Data Index: 724328 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.7102. Min Act: -0.1700

Data Index: 251003 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.6789. Min Act: -0.1700

Data Index: 1163537 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.6789. Min Act: -0.1700

Data Index: 676040 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.6789. Min Act: -0.1700

Data Index: 453148 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.6789. Min Act: -0.1700

Data Index: 500627 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.6789. Min Act: -0.1700

Data Index: 677038 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.6789. Min Act: -0.1700

Data Index: 749626 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.6164. Min Act: -0.1700

Data Index: 911304 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 5.1164. Min Range: -5.1164

Max Act: 4.7102. Min Act: -0.1700

Data Index: 1168841 (C4 (Web Text))

Max Activating Token Index: 407