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

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

Neuron 4338 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0002

Data Index: 252184 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0326. Min Act: -0.0002

Data Index: 100252 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0319. Min Act: -0.0002

Data Index: 780089 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0305. Min Act: -0.0002

Data Index: 608037 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0307. Min Act: -0.0002

Data Index: 599490 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0295. Min Act: -0.0002

Data Index: 586599 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1263985 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1068333 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0309. Min Act: -0.0002

Data Index: 515505 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0268. Min Act: -0.0002

Data Index: 96744 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1250443 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0299. Min Act: -0.0002

Data Index: 786598 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0294. Min Act: -0.0002

Data Index: 165225 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1185048 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0304. Min Act: -0.0002

Data Index: 528421 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1283049 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0266. Min Act: -0.0002

Data Index: 290313 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1076942 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1256077 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0280. Min Act: -0.0002

Data Index: 10678 (C4 (Web Text))

Max Activating Token Index: 307