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

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

Neuron 1519 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1002357 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0000

Data Index: 398078 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0372. Min Act: -0.0000

Data Index: 310706 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0358. Min Act: -0.0000

Data Index: 518354 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0330. Min Act: -0.0000

Data Index: 67115 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1098997 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0352. Min Act: -0.0000

Data Index: 462280 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1170554 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0334. Min Act: -0.0000

Data Index: 80341 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1296635 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1193170 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1173375 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1238307 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0333. Min Act: -0.0000

Data Index: 854589 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0335. Min Act: -0.0000

Data Index: 987734 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0330. Min Act: -0.0000

Data Index: 1107311 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0317. Min Act: -0.0001

Data Index: 556291 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0329. Min Act: -0.0000

Data Index: 456175 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0328. Min Act: -0.0001

Data Index: 192998 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0318. Min Act: -0.0000

Data Index: 843945 (C4 (Web Text))

Max Activating Token Index: 626