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

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

Neuron 320 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3081. Min Act: -0.0000

Data Index: 755306 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2785. Min Act: -0.0000

Data Index: 549853 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2828. Min Act: -0.0000

Data Index: 209508 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2671. Min Act: -0.0000

Data Index: 61307 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1213441 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1264931 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2457. Min Act: -0.0000

Data Index: 620990 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2592. Min Act: -0.0000

Data Index: 810435 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2503. Min Act: -0.0000

Data Index: 411168 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1071972 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2468. Min Act: -0.0000

Data Index: 199519 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1222123 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2466. Min Act: -0.0000

Data Index: 531663 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2422. Min Act: -0.0000

Data Index: 418575 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2425. Min Act: -0.0000

Data Index: 818867 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1034504 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2385. Min Act: -0.0000

Data Index: 559212 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2376. Min Act: -0.0000

Data Index: 36602 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2376. Min Act: -0.0000

Data Index: 29682 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1354044 (C4 (Web Text))

Max Activating Token Index: 74