Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 411 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0431. Min Act: -0.0004

Data Index: 445800 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0003

Data Index: 59246 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0427. Min Act: -0.0003

Data Index: 329578 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1171543 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0406. Min Act: -0.0003

Data Index: 593254 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0407. Min Act: -0.0003

Data Index: 197496 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0415. Min Act: -0.0003

Data Index: 222343 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0406. Min Act: -0.0003

Data Index: 623214 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0397. Min Act: -0.0004

Data Index: 772296 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0400. Min Act: -0.0003

Data Index: 433543 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1147405 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0404. Min Act: -0.0003

Data Index: 400327 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0398. Min Act: -0.0004

Data Index: 703478 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0404. Min Act: -0.0003

Data Index: 84196 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1159205 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0392. Min Act: -0.0003

Data Index: 855351 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0378. Min Act: -0.0003

Data Index: 711724 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0391. Min Act: -0.0003

Data Index: 79649 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1027098 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1205742 (C4 (Web Text))

Max Activating Token Index: 430