Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 677 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0392. Min Act: -0.0001

Data Index: 80890 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0403. Min Act: -0.0001

Data Index: 76757 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1535815 (Python Code)

Max Activating Token Index: 792

Text #3

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0343. Min Act: -0.0001

Data Index: 876800 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0331. Min Act: -0.0001

Data Index: 38522 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1196087 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0320. Min Act: -0.0001

Data Index: 41983 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0336. Min Act: -0.0001

Data Index: 725423 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0316. Min Act: -0.0001

Data Index: 181733 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1387094 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0341. Min Act: -0.0001

Data Index: 475747 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1605927 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1531576 (Python Code)

Max Activating Token Index: 366

Text #13

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1443030 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0334. Min Act: -0.0001

Data Index: 676990 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0354. Min Act: -0.0001

Data Index: 757899 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0325. Min Act: -0.0001

Data Index: 773466 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1528027 (Python Code)

Max Activating Token Index: 323

Text #18

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1565326 (Python Code)

Max Activating Token Index: 711

Text #19

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1136072 (C4 (Web Text))

Max Activating Token Index: 595