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

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

Neuron 2371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0000

Data Index: 307470 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1027035 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0373. Min Act: -0.0000

Data Index: 550618 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1655898 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0283. Min Act: -0.0000

Data Index: 571260 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1325426 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0340. Min Act: -0.0000

Data Index: 80160 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0333. Min Act: -0.0000

Data Index: 799322 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0342. Min Act: -0.0000

Data Index: 243363 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0352. Min Act: -0.0000

Data Index: 277327 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0313. Min Act: -0.0000

Data Index: 241238 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1052427 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1577766 (Python Code)

Max Activating Token Index: 926

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1155273 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0308. Min Act: -0.0000

Data Index: 561152 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0317. Min Act: -0.0000

Data Index: 921902 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0324. Min Act: -0.0000

Data Index: 725866 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0308. Min Act: -0.0000

Data Index: 622345 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0289. Min Act: -0.0000

Data Index: 761710 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0288. Min Act: -0.0000

Data Index: 602841 (C4 (Web Text))

Max Activating Token Index: 746