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

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

Neuron 3716 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: 0.0224. Min Range: -0.0224

Max Act: 0.0224. Min Act: -0.0002

Data Index: 798055 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0209. Min Act: -0.0002

Data Index: 413397 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0209. Min Act: -0.0002

Data Index: 124012 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0194. Min Act: -0.0002

Data Index: 982410 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0190. Min Act: -0.0002

Data Index: 409979 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1260348 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0211. Min Act: -0.0002

Data Index: 166076 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1343608 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1015786 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0189. Min Act: -0.0002

Data Index: 696971 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0193. Min Act: -0.0002

Data Index: 240194 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0204. Min Act: -0.0002

Data Index: 656775 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0194. Min Act: -0.0002

Data Index: 6339 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0204. Min Act: -0.0002

Data Index: 430229 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0204. Min Act: -0.0002

Data Index: 135978 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1112570 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0197. Min Act: -0.0002

Data Index: 396606 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0200. Min Act: -0.0002

Data Index: 42277 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1284366 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0217. Min Act: -0.0002

Data Index: 815511 (C4 (Web Text))

Max Activating Token Index: 105