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

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

Neuron 2976 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0002

Data Index: 435666 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0331. Min Act: -0.0002

Data Index: 265835 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0338. Min Act: -0.0002

Data Index: 317330 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0337. Min Act: -0.0002

Data Index: 743675 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0307. Min Act: -0.0002

Data Index: 850472 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0302. Min Act: -0.0002

Data Index: 214893 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1494181 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1196106 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1577168 (Python Code)

Max Activating Token Index: 79

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0302. Min Act: -0.0002

Data Index: 910355 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1493806 (Python Code)

Max Activating Token Index: 502

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0290. Min Act: -0.0002

Data Index: 313094 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0289. Min Act: -0.0002

Data Index: 460585 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0287. Min Act: -0.0002

Data Index: 720786 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1193414 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1379294 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1019287 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0275. Min Act: -0.0002

Data Index: 216139 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0274. Min Act: -0.0002

Data Index: 691106 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0267. Min Act: -0.0002

Data Index: 206782 (C4 (Web Text))

Max Activating Token Index: 366