Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3249 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0002

Data Index: 455710 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0418. Min Act: -0.0002

Data Index: 985207 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0393. Min Act: -0.0002

Data Index: 698874 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0394. Min Act: -0.0002

Data Index: 205939 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1107511 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0359. Min Act: -0.0003

Data Index: 63459 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0357. Min Act: -0.0002

Data Index: 833633 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0350. Min Act: -0.0003

Data Index: 50959 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0353. Min Act: -0.0002

Data Index: 691319 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0343. Min Act: -0.0002

Data Index: 615759 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1352062 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1047567 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0334. Min Act: -0.0002

Data Index: 229256 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0333. Min Act: -0.0002

Data Index: 845525 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0333. Min Act: -0.0002

Data Index: 915166 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0328. Min Act: -0.0002

Data Index: 384340 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0321. Min Act: -0.0002

Data Index: 315249 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0323. Min Act: -0.0003

Data Index: 170592 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0329. Min Act: -0.0003

Data Index: 890332 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0323. Min Act: -0.0002

Data Index: 656223 (C4 (Web Text))

Max Activating Token Index: 946