Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2039 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0005

Data Index: 459960 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0255. Min Act: -0.0005

Data Index: 718087 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0250. Min Act: -0.0006

Data Index: 25199 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0249. Min Act: -0.0006

Data Index: 9187 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0258. Min Act: -0.0006

Data Index: 774216 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0247. Min Act: -0.0006

Data Index: 100158 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0249. Min Act: -0.0006

Data Index: 579811 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1200529 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0245. Min Act: -0.0006

Data Index: 843469 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0244. Min Act: -0.0006

Data Index: 918419 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0238. Min Act: -0.0006

Data Index: 235352 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0240. Min Act: -0.0006

Data Index: 171495 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0236. Min Act: -0.0006

Data Index: 522452 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1271129 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0240. Min Act: -0.0006

Data Index: 780706 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0232. Min Act: -0.0006

Data Index: 885168 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0237. Min Act: -0.0006

Data Index: 948255 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0221. Min Act: -0.0006

Data Index: 575891 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0223. Min Act: -0.0005

Data Index: 1342394 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0227. Min Act: -0.0006

Data Index: 56841 (C4 (Web Text))

Max Activating Token Index: 494