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

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

Neuron 1654 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: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0002

Data Index: 518661 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0497. Min Act: -0.0002

Data Index: 657167 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0489. Min Act: -0.0002

Data Index: 697332 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1074859 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0403. Min Act: -0.0002

Data Index: 710222 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0388. Min Act: -0.0002

Data Index: 925601 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0407. Min Act: -0.0002

Data Index: 327308 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0386. Min Act: -0.0002

Data Index: 241899 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0374. Min Act: -0.0002

Data Index: 317482 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0378. Min Act: -0.0002

Data Index: 199523 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0378. Min Act: -0.0002

Data Index: 285983 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0362. Min Act: -0.0002

Data Index: 667460 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0361. Min Act: -0.0002

Data Index: 340054 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0353. Min Act: -0.0002

Data Index: 678124 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1151542 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0356. Min Act: -0.0002

Data Index: 593549 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0354. Min Act: -0.0002

Data Index: 851878 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0349. Min Act: -0.0002

Data Index: 347453 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1297166 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0351. Min Act: -0.0002

Data Index: 321244 (C4 (Web Text))

Max Activating Token Index: 160