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

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

Neuron 525 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3555. Min Act: -0.0000

Data Index: 853358 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3463. Min Act: -0.0000

Data Index: 456659 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1041613 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3459. Min Act: -0.0001

Data Index: 724334 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3401. Min Act: -0.0001

Data Index: 390621 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3554. Min Act: -0.0000

Data Index: 961621 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1260199 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3178. Min Act: -0.0000

Data Index: 155410 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3130. Min Act: -0.0000

Data Index: 402488 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3085. Min Act: -0.0000

Data Index: 649297 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3072. Min Act: -0.0000

Data Index: 623771 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3245. Min Act: -0.0001

Data Index: 5387 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3233. Min Act: -0.0000

Data Index: 875579 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3100. Min Act: -0.0001

Data Index: 203183 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3159. Min Act: -0.0000

Data Index: 149178 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3108. Min Act: -0.0000

Data Index: 497294 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3076. Min Act: -0.0000

Data Index: 920375 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2778. Min Act: -0.0001

Data Index: 926136 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3060. Min Act: -0.0001

Data Index: 645912 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1141193 (C4 (Web Text))

Max Activating Token Index: 679