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

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

Neuron 3060 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: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1071723 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0266. Min Act: -0.0002

Data Index: 128545 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0242. Min Act: -0.0002

Data Index: 848476 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0242. Min Act: -0.0002

Data Index: 554262 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1154160 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0236. Min Act: -0.0002

Data Index: 264015 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0226. Min Act: -0.0002

Data Index: 138109 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0211. Min Act: -0.0002

Data Index: 148707 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1032618 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1162675 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1100683 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0193. Min Act: -0.0002

Data Index: 571007 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0188. Min Act: -0.0002

Data Index: 346753 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0178. Min Act: -0.0002

Data Index: 324748 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0189. Min Act: -0.0002

Data Index: 808911 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0170. Min Act: -0.0002

Data Index: 248790 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1304979 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0160. Min Act: -0.0002

Data Index: 158490 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0165. Min Act: -0.0002

Data Index: 821095 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0150. Min Act: -0.0002

Data Index: 750987 (C4 (Web Text))

Max Activating Token Index: 149