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

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

Neuron 587 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0006

Data Index: 536289 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0258. Min Act: -0.0006

Data Index: 796626 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1257527 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1133211 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1007653 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1026579 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0206. Min Act: -0.0006

Data Index: 600575 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0206. Min Act: -0.0006

Data Index: 21869 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0201. Min Act: -0.0006

Data Index: 819467 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1040971 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1350802 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1193528 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0202. Min Act: -0.0006

Data Index: 746621 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1321047 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0197. Min Act: -0.0006

Data Index: 576757 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1026108 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1211141 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0216. Min Act: -0.0006

Data Index: 1300039 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1171264 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0195. Min Act: -0.0006

Data Index: 472556 (C4 (Web Text))

Max Activating Token Index: 302