Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1323 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0188. Min Act: 0.0001

Data Index: 1389536 (Python Code)

Max Activating Token Index: 424

Text #1

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0183. Min Act: -0.0000

Data Index: 821909 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0174. Min Act: 0.0001

Data Index: 725767 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0173. Min Act: 0.0001

Data Index: 935172 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0176. Min Act: 0.0001

Data Index: 1594282 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0172. Min Act: -0.0002

Data Index: 92924 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0175. Min Act: 0.0001

Data Index: 1289703 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0177. Min Act: 0.0001

Data Index: 1239074 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1323504 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1069612 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0179. Min Act: -0.0002

Data Index: 896314 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0165. Min Act: -0.0001

Data Index: 816797 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0171. Min Act: -0.0002

Data Index: 612975 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0167. Min Act: 0.0001

Data Index: 862700 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0171. Min Act: -0.0002

Data Index: 670589 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1524500 (Python Code)

Max Activating Token Index: 386

Text #16

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0169. Min Act: -0.0002

Data Index: 570407 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0165. Min Act: 0.0000

Data Index: 1368650 (Python Code)

Max Activating Token Index: 573

Text #18

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0164. Min Act: -0.0000

Data Index: 535281 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0168. Min Act: -0.0000

Data Index: 239599 (C4 (Web Text))

Max Activating Token Index: 329