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

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

Neuron 2994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1413899 (Python Code)

Max Activating Token Index: 793

Text #1

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0384. Min Act: -0.0001

Data Index: 367457 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1063555 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0375. Min Act: -0.0000

Data Index: 728148 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1415778 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0348. Min Act: -0.0000

Data Index: 913479 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0365. Min Act: -0.0000

Data Index: 1305794 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0363. Min Act: -0.0000

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1291994 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1123505 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0347. Min Act: -0.0001

Data Index: 697854 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0359. Min Act: -0.0001

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1580606 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1463264 (Python Code)

Max Activating Token Index: 185

Text #14

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1258411 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1173300 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0310. Min Act: -0.0001

Data Index: 864719 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1122319 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1495576 (Python Code)

Max Activating Token Index: 939

Text #19

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0308. Min Act: -0.0001

Data Index: 1141234 (C4 (Web Text))

Max Activating Token Index: 535