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

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

Neuron 5220 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1012356 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0384. Min Act: -0.0002

Data Index: 473045 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0383. Min Act: -0.0002

Data Index: 451500 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0374. Min Act: -0.0002

Data Index: 338889 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0350. Min Act: -0.0002

Data Index: 678212 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1643737 (Python Code)

Max Activating Token Index: 862

Text #6

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1063754 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0334. Min Act: -0.0002

Data Index: 370350 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0333. Min Act: -0.0002

Data Index: 545655 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1595091 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0329. Min Act: -0.0002

Data Index: 657876 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0321. Min Act: -0.0002

Data Index: 181880 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0320. Min Act: -0.0002

Data Index: 516009 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1399945 (Python Code)

Max Activating Token Index: 603

Text #14

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0312. Min Act: -0.0002

Data Index: 999162 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1128678 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0316. Min Act: -0.0002

Data Index: 885929 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1349678 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0303. Min Act: -0.0002

Data Index: 763215 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0313. Min Act: -0.0002

Data Index: 37800 (C4 (Web Text))

Max Activating Token Index: 830