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

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

Neuron 2770 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2712. Min Act: -0.0002

Data Index: 752148 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2930. Min Act: -0.0001

Data Index: 374644 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2550. Min Act: -0.0001

Data Index: 219492 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1266697 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2616. Min Act: -0.0002

Data Index: 168995 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2412. Min Act: -0.0002

Data Index: 826881 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2557. Min Act: -0.0002

Data Index: 186845 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2367. Min Act: -0.0001

Data Index: 515704 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2348. Min Act: -0.0002

Data Index: 37187 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2522. Min Act: -0.0001

Data Index: 461397 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2311. Min Act: -0.0001

Data Index: 232563 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2360. Min Act: -0.0001

Data Index: 666370 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2363. Min Act: -0.0001

Data Index: 752427 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2339. Min Act: -0.0002

Data Index: 42361 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2341. Min Act: -0.0002

Data Index: 1157396 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2390. Min Act: -0.0001

Data Index: 705760 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2321. Min Act: -0.0002

Data Index: 472774 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2152. Min Act: -0.0002

Data Index: 327425 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2303. Min Act: -0.0002

Data Index: 579329 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1208069 (C4 (Web Text))

Max Activating Token Index: 3