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

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

Neuron 3422 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0346. Min Act: -0.0000

Data Index: 54839 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1006907 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1012091 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9020. Min Act: -0.0000

Data Index: 188303 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1357661 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8244. Min Act: -0.0000

Data Index: 829636 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8187. Min Act: -0.0000

Data Index: 116459 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8324. Min Act: -0.0000

Data Index: 495347 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8339. Min Act: -0.0000

Data Index: 954450 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8037. Min Act: -0.0000

Data Index: 259808 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7604. Min Act: -0.0000

Data Index: 212454 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1084749 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.6314. Min Act: -0.0000

Data Index: 307947 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.6289. Min Act: -0.0000

Data Index: 191700 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.6130. Min Act: -0.0000

Data Index: 444077 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1089091 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.5616. Min Act: -0.0000

Data Index: 327466 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.5368. Min Act: -0.0000

Data Index: 228438 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.5147. Min Act: -0.0000

Data Index: 222857 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1333789 (C4 (Web Text))

Max Activating Token Index: 492