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

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

Neuron 2010 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.6219. Min Act: -0.1700

Data Index: 762328 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5592. Min Act: -0.1700

Data Index: 1065055 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5436. Min Act: -0.1700

Data Index: 704643 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5436. Min Act: -0.1700

Data Index: 688548 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5279. Min Act: -0.1700

Data Index: 736384 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5123. Min Act: -0.1700

Data Index: 824365 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.4966. Min Act: -0.1700

Data Index: 1046330 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5279. Min Act: -0.1700

Data Index: 398884 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5279. Min Act: -0.1700

Data Index: 93700 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.4966. Min Act: -0.1700

Data Index: 599082 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5123. Min Act: -0.1700

Data Index: 592897 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5279. Min Act: -0.1700

Data Index: 831526 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.5123. Min Act: -0.1700

Data Index: 1332339 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.4966. Min Act: -0.1700

Data Index: 91139 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.4809. Min Act: -0.1700

Data Index: 765624 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.4496. Min Act: -0.1700

Data Index: 1411788 (Python Code)

Max Activating Token Index: 958

Text #16

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.4652. Min Act: -0.1700

Data Index: 1041883 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.4652. Min Act: -0.1700

Data Index: 199114 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.4496. Min Act: -0.1700

Data Index: 677425 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 3.6219. Min Range: -3.6219

Max Act: 3.4652. Min Act: -0.1700

Data Index: 1028679 (C4 (Web Text))

Max Activating Token Index: 881