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

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

Neuron 649 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0216. Min Act: -0.0000

Data Index: 520948 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0212. Min Act: -0.0000

Data Index: 1249634 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0198. Min Act: -0.0000

Data Index: 448986 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0204. Min Act: -0.0000

Data Index: 684756 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0188. Min Act: -0.0000

Data Index: 1083195 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0186. Min Act: -0.0000

Data Index: 1085504 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0177. Min Act: -0.0000

Data Index: 396953 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0183. Min Act: -0.0000

Data Index: 1285357 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0182. Min Act: -0.0000

Data Index: 1272527 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0163. Min Act: -0.0000

Data Index: 460837 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0185. Min Act: -0.0000

Data Index: 83823 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0177. Min Act: -0.0000

Data Index: 1305616 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0168. Min Act: -0.0000

Data Index: 1250798 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0178. Min Act: -0.0000

Data Index: 398091 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0158. Min Act: -0.0000

Data Index: 931168 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0163. Min Act: -0.0000

Data Index: 622087 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0166. Min Act: -0.0000

Data Index: 247998 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0159. Min Act: -0.0000

Data Index: 327017 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0155. Min Act: -0.0000

Data Index: 848710 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0155. Min Act: -0.0000

Data Index: 1245467 (C4 (Web Text))

Max Activating Token Index: 985