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

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

Neuron 2776 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.8207. Min Act: -0.0000

Data Index: 278671 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7757. Min Act: -0.0000

Data Index: 519198 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1306961 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7002. Min Act: -0.0000

Data Index: 645825 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7375. Min Act: -0.0000

Data Index: 79773 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6660. Min Act: -0.0000

Data Index: 21328 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6636. Min Act: -0.0000

Data Index: 80327 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6356. Min Act: -0.0000

Data Index: 925041 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6476. Min Act: -0.0000

Data Index: 1208679 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6228. Min Act: -0.0000

Data Index: 746968 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6406. Min Act: -0.0000

Data Index: 750894 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6187. Min Act: -0.0000

Data Index: 769020 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1291332 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6169. Min Act: -0.0000

Data Index: 649463 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6314. Min Act: -0.0000

Data Index: 539432 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6117. Min Act: -0.0000

Data Index: 516019 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6268. Min Act: -0.0000

Data Index: 472422 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1338437 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6343. Min Act: -0.0000

Data Index: 191956 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1160262 (C4 (Web Text))

Max Activating Token Index: 186