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

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

Neuron 3560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.3295. Min Act: -0.0002

Data Index: 535359 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2918. Min Act: -0.0002

Data Index: 174285 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2568. Min Act: -0.0002

Data Index: 674206 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2556. Min Act: -0.0002

Data Index: 668384 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2476. Min Act: -0.0002

Data Index: 1120429 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2452. Min Act: -0.0002

Data Index: 217856 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2389. Min Act: -0.0002

Data Index: 472947 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2351. Min Act: -0.0002

Data Index: 24976 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2482. Min Act: -0.0002

Data Index: 27562 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2337. Min Act: -0.0002

Data Index: 396787 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2270. Min Act: -0.0002

Data Index: 1096925 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2126. Min Act: -0.0002

Data Index: 921335 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2234. Min Act: -0.0002

Data Index: 746035 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2170. Min Act: -0.0002

Data Index: 243490 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2184. Min Act: -0.0002

Data Index: 114928 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2107. Min Act: -0.0002

Data Index: 387615 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2083. Min Act: -0.0002

Data Index: 55468 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2208. Min Act: -0.0002

Data Index: 934451 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2161. Min Act: -0.0002

Data Index: 746995 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2053. Min Act: -0.0002

Data Index: 1131565 (C4 (Web Text))

Max Activating Token Index: 185