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

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

Neuron 2317 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1044356 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0352. Min Act: -0.0001

Data Index: 374787 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1022274 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0302. Min Act: -0.0001

Data Index: 192413 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0254. Min Act: -0.0001

Data Index: 847244 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0237. Min Act: -0.0001

Data Index: 326704 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0218. Min Act: -0.0001

Data Index: 154152 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1153412 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0230. Min Act: -0.0001

Data Index: 512088 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0210. Min Act: -0.0001

Data Index: 575 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0208. Min Act: -0.0001

Data Index: 336342 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0207. Min Act: -0.0001

Data Index: 700545 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0210. Min Act: -0.0001

Data Index: 416826 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0212. Min Act: -0.0001

Data Index: 492020 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1095048 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0207. Min Act: -0.0001

Data Index: 238998 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1096248 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0199. Min Act: -0.0001

Data Index: 970726 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0198. Min Act: -0.0001

Data Index: 457946 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0194. Min Act: -0.0001

Data Index: 951176 (C4 (Web Text))

Max Activating Token Index: 15