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

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

Neuron 3071 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1224718 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0598. Min Act: -0.0003

Data Index: 401305 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0516. Min Act: -0.0003

Data Index: 559175 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0491. Min Act: -0.0003

Data Index: 691800 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0442. Min Act: -0.0002

Data Index: 394981 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0448. Min Act: -0.0003

Data Index: 265976 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0426. Min Act: -0.0003

Data Index: 160698 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0434. Min Act: -0.0002

Data Index: 258228 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0414. Min Act: -0.0002

Data Index: 34182 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0416. Min Act: -0.0003

Data Index: 315274 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0408. Min Act: -0.0003

Data Index: 938612 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0400. Min Act: -0.0003

Data Index: 417228 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0396. Min Act: -0.0003

Data Index: 571764 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0386. Min Act: -0.0003

Data Index: 936639 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0376. Min Act: -0.0003

Data Index: 826112 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1034576 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1033747 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0366. Min Act: -0.0003

Data Index: 684803 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1290390 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1194894 (C4 (Web Text))

Max Activating Token Index: 48