Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 187 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.8407. Min Act: -0.0001

Data Index: 96853 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.7941. Min Act: -0.0000

Data Index: 343365 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.7007. Min Act: -0.0001

Data Index: 1073554 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.7051. Min Act: -0.0001

Data Index: 31669 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1242983 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6629. Min Act: -0.0001

Data Index: 724415 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.7001. Min Act: -0.0001

Data Index: 131934 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6803. Min Act: -0.0001

Data Index: 963443 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6971. Min Act: -0.0000

Data Index: 518915 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6577. Min Act: -0.0000

Data Index: 867277 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.7476. Min Act: -0.0001

Data Index: 295121 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6591. Min Act: -0.0001

Data Index: 997042 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6438. Min Act: -0.0001

Data Index: 144955 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6171. Min Act: -0.0000

Data Index: 483447 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6331. Min Act: -0.0000

Data Index: 88218 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6125. Min Act: -0.0001

Data Index: 474235 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6473. Min Act: -0.0001

Data Index: 579761 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6243. Min Act: -0.0001

Data Index: 525596 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6197. Min Act: -0.0001

Data Index: 613785 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.5984. Min Act: -0.0000

Data Index: 671759 (C4 (Web Text))

Max Activating Token Index: 666