Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3741 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0336. Min Act: -0.0000

Data Index: 655418 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1431024 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0000

Data Index: 617453 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0292. Min Act: -0.0000

Data Index: 197822 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0289. Min Act: -0.0000

Data Index: 950757 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0288. Min Act: -0.0000

Data Index: 473655 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0274. Min Act: -0.0001

Data Index: 610624 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0285. Min Act: -0.0000

Data Index: 1524200 (Python Code)

Max Activating Token Index: 624

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0289. Min Act: -0.0000

Data Index: 48476 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0273. Min Act: -0.0000

Data Index: 789274 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0263. Min Act: -0.0000

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0271. Min Act: -0.0000

Data Index: 585872 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0268. Min Act: -0.0001

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0266. Min Act: -0.0000

Data Index: 216498 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0254. Min Act: -0.0000

Data Index: 937855 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0284. Min Act: -0.0000

Data Index: 1025273 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0255. Min Act: -0.0000

Data Index: 1551012 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1203283 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0244. Min Act: -0.0000

Data Index: 520565 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0250. Min Act: -0.0000

Data Index: 400181 (C4 (Web Text))

Max Activating Token Index: 923