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

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

Neuron 1215 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0382. Min Act: -0.0006

Data Index: 1306389 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0389. Min Act: -0.0006

Data Index: 622707 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0382. Min Act: -0.0006

Data Index: 313896 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0377. Min Act: -0.0006

Data Index: 307175 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0378. Min Act: -0.0006

Data Index: 418805 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1127613 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0356. Min Act: -0.0006

Data Index: 215472 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0369. Min Act: -0.0006

Data Index: 1141906 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0362. Min Act: -0.0006

Data Index: 449545 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0361. Min Act: -0.0006

Data Index: 1244552 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0358. Min Act: -0.0006

Data Index: 434213 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0348. Min Act: -0.0006

Data Index: 298889 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0351. Min Act: -0.0006

Data Index: 560729 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0347. Min Act: -0.0006

Data Index: 1090977 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0340. Min Act: -0.0006

Data Index: 976885 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1248099 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0338. Min Act: -0.0006

Data Index: 549795 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0343. Min Act: -0.0006

Data Index: 1302643 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0343. Min Act: -0.0006

Data Index: 1006094 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0347. Min Act: -0.0007

Data Index: 1115068 (C4 (Web Text))

Max Activating Token Index: 334