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

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

Neuron 135 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1384467 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3931. Min Act: -0.0000

Data Index: 121380 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3648. Min Act: 0.0000

Data Index: 630141 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3737. Min Act: 0.0000

Data Index: 71254 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1327693 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3340. Min Act: -0.0000

Data Index: 565302 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3382. Min Act: -0.0000

Data Index: 308515 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3506. Min Act: 0.0000

Data Index: 306257 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1313090 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3385. Min Act: -0.0000

Data Index: 683853 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3077. Min Act: 0.0000

Data Index: 802334 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3076. Min Act: 0.0002

Data Index: 236890 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3204. Min Act: 0.0001

Data Index: 734553 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1050442 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3191. Min Act: 0.0000

Data Index: 907666 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3178. Min Act: 0.0000

Data Index: 1028713 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3186. Min Act: -0.0000

Data Index: 310226 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3016. Min Act: -0.0000

Data Index: 585017 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3102. Min Act: -0.0000

Data Index: 451159 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1198285 (C4 (Web Text))

Max Activating Token Index: 125