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

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

Neuron 2037 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1223. Min Range: -5.1223

Max Act: 5.0910. Min Act: -0.1700

Data Index: 1153521 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 5.1223. Min Range: -5.1223

Max Act: 5.1223. Min Act: -0.1700

Data Index: 737193 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 5.1223. Min Range: -5.1223

Max Act: 5.0285. Min Act: -0.1700

Data Index: 568389 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 5.1223. Min Range: -5.1223

Max Act: 5.0598. Min Act: -0.1699

Data Index: 383810 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.9660. Min Act: -0.1700

Data Index: 1129519 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.8723. Min Act: -0.1698

Data Index: 1308014 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.8098. Min Act: -0.1700

Data Index: 772946 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.9348. Min Act: -0.1700

Data Index: 1058576 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.8098. Min Act: -0.1700

Data Index: 761140 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.8098. Min Act: -0.1700

Data Index: 391031 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.8098. Min Act: -0.1700

Data Index: 541228 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.7785. Min Act: -0.1700

Data Index: 677928 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.7160. Min Act: -0.1699

Data Index: 12609 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.7785. Min Act: -0.1700

Data Index: 1035264 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.7473. Min Act: -0.1700

Data Index: 965613 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.7473. Min Act: -0.1700

Data Index: 140185 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.6848. Min Act: -0.1700

Data Index: 967200 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.6535. Min Act: -0.1700

Data Index: 1023228 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.6848. Min Act: -0.1700

Data Index: 381193 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 5.1223. Min Range: -5.1223

Max Act: 4.7785. Min Act: -0.1700

Data Index: 119633 (C4 (Web Text))

Max Activating Token Index: 366