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

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

Neuron 1578 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: 0.0337. Min Range: -0.0337

Max Act: 0.0333. Min Act: -0.0006

Data Index: 822186 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0337. Min Act: -0.0006

Data Index: 1440663 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0326. Min Act: -0.0006

Data Index: 362368 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0303. Min Act: -0.0006

Data Index: 581807 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1210221 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0293. Min Act: -0.0006

Data Index: 152816 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0265. Min Act: -0.0006

Data Index: 466038 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1286816 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0262. Min Act: -0.0006

Data Index: 35250 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0266. Min Act: -0.0006

Data Index: 532977 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1155397 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0267. Min Act: -0.0006

Data Index: 996477 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0265. Min Act: -0.0006

Data Index: 818420 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0264. Min Act: -0.0006

Data Index: 1162532 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1098521 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0257. Min Act: -0.0006

Data Index: 713548 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0267. Min Act: -0.0006

Data Index: 316197 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1287259 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0265. Min Act: -0.0006

Data Index: 785520 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0243. Min Act: -0.0006

Data Index: 696757 (C4 (Web Text))

Max Activating Token Index: 783