Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2409 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0001

Data Index: 67826 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1469821 (Python Code)

Max Activating Token Index: 639

Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1051186 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0206. Min Act: -0.0001

Data Index: 708458 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0201. Min Act: -0.0001

Data Index: 570188 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0197. Min Act: -0.0001

Data Index: 934749 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0198. Min Act: -0.0001

Data Index: 581815 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0197. Min Act: -0.0001

Data Index: 650902 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0202. Min Act: -0.0001

Data Index: 921525 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0178. Min Act: -0.0001

Data Index: 117963 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0188. Min Act: -0.0001

Data Index: 169590 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0203. Min Act: -0.0001

Data Index: 17102 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0179. Min Act: -0.0001

Data Index: 849648 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0183. Min Act: -0.0001

Data Index: 189549 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1115120 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0175. Min Act: -0.0001

Data Index: 382073 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0175. Min Act: -0.0001

Data Index: 589448 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1545367 (Python Code)

Max Activating Token Index: 612

Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0161. Min Act: -0.0001

Data Index: 569393 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1112204 (C4 (Web Text))

Max Activating Token Index: 539