Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 48 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3477. Min Act: -0.0000

Data Index: 506974 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1519464 (Python Code)

Max Activating Token Index: 493

Text #2

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2669. Min Act: -0.0000

Data Index: 259772 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2388. Min Act: -0.0000

Data Index: 629906 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1182238 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2402. Min Act: -0.0000

Data Index: 50939 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2583. Min Act: -0.0000

Data Index: 306911 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2462. Min Act: -0.0000

Data Index: 481883 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2413. Min Act: -0.0000

Data Index: 483505 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2317. Min Act: -0.0000

Data Index: 15774 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1625341 (Python Code)

Max Activating Token Index: 986

Text #11

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2311. Min Act: -0.0000

Data Index: 345532 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2235. Min Act: -0.0000

Data Index: 157754 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2234. Min Act: -0.0000

Data Index: 925486 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1364875 (Python Code)

Max Activating Token Index: 437

Text #15

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2221. Min Act: -0.0000

Data Index: 612839 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2128. Min Act: -0.0000

Data Index: 424002 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2287. Min Act: -0.0000

Data Index: 502120 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1208461 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1010027 (C4 (Web Text))

Max Activating Token Index: 826