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

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

Neuron 2409 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1582182 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2920. Min Act: -0.0000

Data Index: 635068 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2802. Min Act: -0.0001

Data Index: 427647 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2730. Min Act: -0.0000

Data Index: 242673 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2582. Min Act: -0.0001

Data Index: 159479 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2638. Min Act: -0.0000

Data Index: 946282 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2718. Min Act: -0.0001

Data Index: 356191 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2518. Min Act: -0.0001

Data Index: 980461 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1403579 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2573. Min Act: -0.0000

Data Index: 723325 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1388507 (Python Code)

Max Activating Token Index: 288

Text #11

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2339. Min Act: -0.0001

Data Index: 411897 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2586. Min Act: -0.0000

Data Index: 389536 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2640. Min Act: -0.0001

Data Index: 789129 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1062310 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1364893 (Python Code)

Max Activating Token Index: 371

Text #16

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1218304 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2360. Min Act: -0.0001

Data Index: 635233 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2777. Min Act: -0.0001

Data Index: 526252 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2484. Min Act: -0.0000

Data Index: 474792 (C4 (Web Text))

Max Activating Token Index: 387