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

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

Neuron 294 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0350. Min Act: -0.0002

Data Index: 68997 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1067963 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1096398 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0349. Min Act: -0.0003

Data Index: 623423 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0346. Min Act: -0.0003

Data Index: 543334 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1296420 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0339. Min Act: -0.0003

Data Index: 850572 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0003

Data Index: 857932 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0337. Min Act: -0.0003

Data Index: 737438 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0340. Min Act: -0.0003

Data Index: 622485 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1030169 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1015089 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0325. Min Act: -0.0004

Data Index: 467266 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0328. Min Act: -0.0004

Data Index: 540064 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0331. Min Act: -0.0004

Data Index: 1179835 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0334. Min Act: -0.0003

Data Index: 925158 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1166115 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0326. Min Act: -0.0003

Data Index: 778842 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0323. Min Act: -0.0003

Data Index: 471309 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0340. Min Act: -0.0003

Data Index: 71656 (C4 (Web Text))

Max Activating Token Index: 1018