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

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

Neuron 585 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0385. Min Act: -0.0002

Data Index: 904968 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0384. Min Act: -0.0002

Data Index: 575635 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0374. Min Act: -0.0002

Data Index: 603570 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0343. Min Act: -0.0002

Data Index: 280745 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0367. Min Act: -0.0002

Data Index: 618704 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1260363 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0368. Min Act: -0.0002

Data Index: 503478 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0362. Min Act: -0.0002

Data Index: 68616 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0363. Min Act: -0.0002

Data Index: 807577 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0368. Min Act: -0.0002

Data Index: 27697 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0347. Min Act: -0.0002

Data Index: 187179 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0338. Min Act: -0.0002

Data Index: 273834 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0355. Min Act: -0.0002

Data Index: 112547 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0340. Min Act: -0.0002

Data Index: 902775 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0345. Min Act: -0.0002

Data Index: 11748 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0334. Min Act: -0.0002

Data Index: 950608 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1215488 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0332. Min Act: -0.0002

Data Index: 364530 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0325. Min Act: -0.0002

Data Index: 942948 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0320. Min Act: -0.0002

Data Index: 459793 (C4 (Web Text))

Max Activating Token Index: 784