Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1521 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0321. Min Act: -0.0006

Data Index: 217349 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0277. Min Act: -0.0006

Data Index: 61615 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0265. Min Act: -0.0006

Data Index: 712511 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1070761 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1022072 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0268. Min Act: -0.0006

Data Index: 861596 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1110183 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0265. Min Act: -0.0006

Data Index: 941493 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1192765 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0257. Min Act: -0.0006

Data Index: 382415 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0262. Min Act: -0.0006

Data Index: 373545 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1129310 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1226427 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0241. Min Act: -0.0006

Data Index: 286937 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0269. Min Act: -0.0006

Data Index: 192076 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0239. Min Act: -0.0006

Data Index: 740104 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0250. Min Act: -0.0006

Data Index: 972016 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1132924 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0255. Min Act: -0.0006

Data Index: 961653 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1145845 (C4 (Web Text))

Max Activating Token Index: 556