Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 78 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.2507. Min Act: -0.1700

Data Index: 1314870 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.2195. Min Act: -0.1700

Data Index: 452338 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.1257. Min Act: -0.1700

Data Index: 338687 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0945. Min Act: -0.1700

Data Index: 672832 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0632. Min Act: -0.1700

Data Index: 1213461 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0632. Min Act: -0.1700

Data Index: 844041 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0945. Min Act: -0.1700

Data Index: 185348 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0320. Min Act: -0.1700

Data Index: 314970 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0320. Min Act: -0.1700

Data Index: 6747 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0632. Min Act: -0.1700

Data Index: 993440 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0632. Min Act: -0.1700

Data Index: 369379 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0320. Min Act: -0.1700

Data Index: 1126276 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 5.2507. Min Range: -5.2507

Max Act: 4.9695. Min Act: -0.1700

Data Index: 1072052 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0007. Min Act: -0.1700

Data Index: 980515 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0320. Min Act: -0.1700

Data Index: 492799 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 5.2507. Min Range: -5.2507

Max Act: 4.9695. Min Act: -0.1700

Data Index: 364589 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 5.2507. Min Range: -5.2507

Max Act: 4.9382. Min Act: -0.1700

Data Index: 318794 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 5.2507. Min Range: -5.2507

Max Act: 5.0007. Min Act: -0.1700

Data Index: 447503 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 5.2507. Min Range: -5.2507

Max Act: 4.9382. Min Act: -0.1700

Data Index: 291925 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 5.2507. Min Range: -5.2507

Max Act: 4.9695. Min Act: -0.1700

Data Index: 212384 (C4 (Web Text))

Max Activating Token Index: 818