Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 476 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.6176. Min Act: -0.0000

Data Index: 410560 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.7391. Min Act: -0.0000

Data Index: 611355 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.4678. Min Act: -0.0001

Data Index: 467015 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.5138. Min Act: -0.0000

Data Index: 675526 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.1989. Min Act: -0.0001

Data Index: 530712 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.2959. Min Act: -0.0000

Data Index: 1171188 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.3140. Min Act: -0.0000

Data Index: 1351677 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.1020. Min Act: -0.0000

Data Index: 144768 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.2542. Min Act: -0.0000

Data Index: 271039 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.2433. Min Act: -0.0001

Data Index: 406089 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.0854. Min Act: -0.0000

Data Index: 20550 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.1705. Min Act: -0.0001

Data Index: 1102131 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.0965. Min Act: -0.0001

Data Index: 1152829 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 2.7391. Min Range: -2.7391

Max Act: 1.9040. Min Act: -0.0000

Data Index: 893013 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 2.7391. Min Range: -2.7391

Max Act: 1.9688. Min Act: -0.0000

Data Index: 115539 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.0616. Min Act: -0.0000

Data Index: 812221 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.1612. Min Act: -0.0000

Data Index: 54887 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 2.7391. Min Range: -2.7391

Max Act: 1.9361. Min Act: -0.0000

Data Index: 620744 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.0234. Min Act: -0.0000

Data Index: 1054700 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 2.7391. Min Range: -2.7391

Max Act: 2.1498. Min Act: -0.0000

Data Index: 57991 (C4 (Web Text))

Max Activating Token Index: 749