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

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

Neuron 3245 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6151. Min Range: -4.6151

Max Act: 4.6151. Min Act: -0.0000

Data Index: 448838 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 4.6151. Min Range: -4.6151

Max Act: 4.3545. Min Act: -0.0000

Data Index: 94330 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.8530. Min Act: -0.0000

Data Index: 650341 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 4.6151. Min Range: -4.6151

Max Act: 4.0923. Min Act: -0.0000

Data Index: 247763 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.6768. Min Act: -0.0000

Data Index: 1142051 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.9484. Min Act: -0.0000

Data Index: 590729 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.7372. Min Act: -0.0000

Data Index: 1243948 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.7333. Min Act: -0.0000

Data Index: 916497 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.8338. Min Act: -0.0000

Data Index: 1285232 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.4602. Min Act: -0.0000

Data Index: 734049 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.4687. Min Act: -0.0000

Data Index: 1126713 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.5119. Min Act: -0.0000

Data Index: 377100 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.5378. Min Act: -0.0000

Data Index: 230240 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.5712. Min Act: -0.0000

Data Index: 8119 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.2277. Min Act: -0.0000

Data Index: 907132 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.5263. Min Act: -0.0000

Data Index: 829249 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.6606. Min Act: -0.0000

Data Index: 315108 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.4676. Min Act: -0.0000

Data Index: 1080463 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.2607. Min Act: -0.0000

Data Index: 1112910 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 4.6151. Min Range: -4.6151

Max Act: 3.4242. Min Act: -0.0000

Data Index: 599563 (C4 (Web Text))

Max Activating Token Index: 587