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

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

Neuron 1138 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0285. Min Act: -0.0006

Data Index: 318681 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0276. Min Act: -0.0006

Data Index: 841907 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0276. Min Act: -0.0006

Data Index: 47725 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0284. Min Act: -0.0006

Data Index: 545444 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0270. Min Act: -0.0006

Data Index: 271288 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0261. Min Act: -0.0006

Data Index: 535848 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0260. Min Act: -0.0006

Data Index: 32298 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0251. Min Act: -0.0006

Data Index: 556562 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0245. Min Act: -0.0006

Data Index: 704616 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0250. Min Act: -0.0006

Data Index: 410022 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1342837 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0234. Min Act: -0.0006

Data Index: 498974 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0235. Min Act: -0.0006

Data Index: 695577 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0240. Min Act: -0.0006

Data Index: 84348 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0244. Min Act: -0.0006

Data Index: 32035 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1241807 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0236. Min Act: -0.0006

Data Index: 495058 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1280666 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0223. Min Act: -0.0006

Data Index: 869263 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0234. Min Act: -0.0006

Data Index: 805547 (C4 (Web Text))

Max Activating Token Index: 163