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

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

Neuron 1474 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0165. Min Range: -7.0165

Max Act: 7.0165. Min Act: -0.1699

Data Index: 1317923 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 7.0165. Min Range: -7.0165

Max Act: 7.0165. Min Act: -0.1699

Data Index: 535684 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.8915. Min Act: -0.1699

Data Index: 1039416 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 7.0165. Min Range: -7.0165

Max Act: 7.0165. Min Act: -0.1700

Data Index: 650778 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.8915. Min Act: -0.1699

Data Index: 656375 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.8290. Min Act: -0.1700

Data Index: 780725 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.7978. Min Act: -0.1700

Data Index: 138294 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.9540. Min Act: -0.1700

Data Index: 110033 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.7353. Min Act: -0.1700

Data Index: 947271 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.8603. Min Act: -0.1700

Data Index: 252466 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.7665. Min Act: -0.1700

Data Index: 134137 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.7665. Min Act: -0.1699

Data Index: 1054814 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.7665. Min Act: -0.1700

Data Index: 593362 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.7353. Min Act: -0.1700

Data Index: 891642 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.6728. Min Act: -0.1700

Data Index: 55956 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.7040. Min Act: -0.1700

Data Index: 1114007 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.6415. Min Act: -0.1700

Data Index: 460798 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.7040. Min Act: -0.1700

Data Index: 1099079 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.7040. Min Act: -0.1700

Data Index: 670266 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 7.0165. Min Range: -7.0165

Max Act: 6.6728. Min Act: -0.1700

Data Index: 469976 (C4 (Web Text))

Max Activating Token Index: 76