Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 666 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1037. Min Range: -1.1037

Max Act: 1.1037. Min Act: -0.0000

Data Index: 482385 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1304439 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8926. Min Act: -0.0000

Data Index: 47303 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1098286 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8260. Min Act: -0.0000

Data Index: 883763 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.7380. Min Act: -0.0000

Data Index: 146733 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.7520. Min Act: -0.0000

Data Index: 666815 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1066715 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1128017 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1154813 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1126135 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1122853 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.6307. Min Act: -0.0000

Data Index: 807593 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1056168 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.6060. Min Act: -0.0000

Data Index: 277217 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.6345. Min Act: -0.0000

Data Index: 934959 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1260483 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1091214 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.6356. Min Act: -0.0000

Data Index: 159929 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.5707. Min Act: -0.0000

Data Index: 72998 (C4 (Web Text))

Max Activating Token Index: 263