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

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

Neuron 4023 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0004

Data Index: 722215 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0477. Min Act: -0.0004

Data Index: 74133 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1187674 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0467. Min Act: -0.0003

Data Index: 230015 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0450. Min Act: -0.0003

Data Index: 908637 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1315001 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1104815 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1130156 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0423. Min Act: -0.0003

Data Index: 823361 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0393. Min Act: -0.0003

Data Index: 550020 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0427. Min Act: -0.0003

Data Index: 321401 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0424. Min Act: -0.0003

Data Index: 366247 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0438. Min Act: -0.0003

Data Index: 791793 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0439. Min Act: -0.0003

Data Index: 126749 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0373. Min Act: -0.0003

Data Index: 878337 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0406. Min Act: -0.0003

Data Index: 619078 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0404. Min Act: -0.0003

Data Index: 640878 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0387. Min Act: -0.0003

Data Index: 387053 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0364. Min Act: -0.0003

Data Index: 198226 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0397. Min Act: -0.0003

Data Index: 266294 (C4 (Web Text))

Max Activating Token Index: 315