Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2434 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1345948 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0269. Min Act: -0.0002

Data Index: 157810 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0258. Min Act: -0.0002

Data Index: 330451 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0258. Min Act: -0.0002

Data Index: 677149 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0257. Min Act: -0.0002

Data Index: 341618 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0235. Min Act: -0.0002

Data Index: 779704 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1067710 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0233. Min Act: -0.0002

Data Index: 281748 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1284494 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1345365 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0198. Min Act: -0.0002

Data Index: 931033 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0203. Min Act: -0.0002

Data Index: 371031 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0194. Min Act: -0.0002

Data Index: 63395 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1542511 (Python Code)

Max Activating Token Index: 235

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0182. Min Act: -0.0002

Data Index: 67981 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1185455 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1172357 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1211847 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0179. Min Act: -0.0002

Data Index: 423590 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1222161 (C4 (Web Text))

Max Activating Token Index: 924