Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1056 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0209. Min Act: -0.0004

Data Index: 1012580 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1350407 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0206. Min Act: -0.0005

Data Index: 604956 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0195. Min Act: -0.0005

Data Index: 814392 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0192. Min Act: -0.0005

Data Index: 801568 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0188. Min Act: -0.0005

Data Index: 717693 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1495063 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1496471 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0171. Min Act: -0.0005

Data Index: 571175 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1374812 (Python Code)

Max Activating Token Index: 727

Text #10

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0176. Min Act: -0.0004

Data Index: 762875 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1651480 (Python Code)

Max Activating Token Index: 824

Text #12

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0176. Min Act: -0.0004

Data Index: 1634289 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1578208 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0178. Min Act: -0.0005

Data Index: 772994 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0170. Min Act: -0.0005

Data Index: 681733 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0172. Min Act: -0.0004

Data Index: 1408540 (Python Code)

Max Activating Token Index: 680

Text #17

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0172. Min Act: -0.0005

Data Index: 310631 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1507224 (Python Code)

Max Activating Token Index: 609

Text #19

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0172. Min Act: -0.0004

Data Index: 779885 (C4 (Web Text))

Max Activating Token Index: 308