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

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

Neuron 1109 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: 3.3385. Min Range: -3.3385

Max Act: 3.3385. Min Act: -0.1700

Data Index: 411614 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.3228. Min Act: -0.1700

Data Index: 1141096 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.3385. Min Act: -0.1700

Data Index: 1197699 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.3385. Min Act: -0.1700

Data Index: 676710 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.3228. Min Act: -0.1700

Data Index: 444449 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.3385. Min Act: -0.1700

Data Index: 1334208 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.3228. Min Act: -0.1700

Data Index: 345384 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.3071. Min Act: -0.1700

Data Index: 164861 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.3071. Min Act: -0.1700

Data Index: 838740 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2757. Min Act: -0.1700

Data Index: 1459314 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.3071. Min Act: -0.1700

Data Index: 171851 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2600. Min Act: -0.1700

Data Index: 904266 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2914. Min Act: -0.1700

Data Index: 138006 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2914. Min Act: -0.1700

Data Index: 277094 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2757. Min Act: -0.1700

Data Index: 1196611 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2914. Min Act: -0.1700

Data Index: 922613 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2757. Min Act: -0.1700

Data Index: 201383 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2914. Min Act: -0.1700

Data Index: 1293204 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2914. Min Act: -0.1700

Data Index: 280625 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 3.3385. Min Range: -3.3385

Max Act: 3.2757. Min Act: -0.1700

Data Index: 1321281 (C4 (Web Text))

Max Activating Token Index: 454