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

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

Neuron 1921 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: 0.4020. Min Range: -0.4020

Max Act: 0.4020. Min Act: -0.0001

Data Index: 1234371 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3924. Min Act: -0.0001

Data Index: 398588 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3924. Min Act: -0.0001

Data Index: 805341 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3739. Min Act: -0.0001

Data Index: 932810 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1293796 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3571. Min Act: -0.0001

Data Index: 886548 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3299. Min Act: -0.0001

Data Index: 745169 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3255. Min Act: -0.0000

Data Index: 420669 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3262. Min Act: -0.0000

Data Index: 253388 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3135. Min Act: -0.0001

Data Index: 2433 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3000. Min Act: -0.0001

Data Index: 341979 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3197. Min Act: -0.0000

Data Index: 963553 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3174. Min Act: -0.0001

Data Index: 138619 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3126. Min Act: -0.0001

Data Index: 655656 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1077883 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3113. Min Act: -0.0000

Data Index: 533998 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3091. Min Act: -0.0001

Data Index: 346824 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1154854 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3084. Min Act: -0.0001

Data Index: 681459 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.4020. Min Range: -0.4020

Max Act: 0.3013. Min Act: -0.0001

Data Index: 887823 (C4 (Web Text))

Max Activating Token Index: 411