Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1053 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0004

Data Index: 1008096 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0380. Min Act: -0.0004

Data Index: 471825 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1355645 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1035346 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0354. Min Act: -0.0003

Data Index: 615956 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0348. Min Act: -0.0003

Data Index: 902412 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0338. Min Act: -0.0003

Data Index: 896640 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0351. Min Act: -0.0004

Data Index: 1325602 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0350. Min Act: -0.0004

Data Index: 252926 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0343. Min Act: -0.0003

Data Index: 697264 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0334. Min Act: -0.0002

Data Index: 748998 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0339. Min Act: -0.0003

Data Index: 522820 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0332. Min Act: -0.0003

Data Index: 817302 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0339. Min Act: -0.0004

Data Index: 637753 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0328. Min Act: -0.0003

Data Index: 55210 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0335. Min Act: -0.0003

Data Index: 348630 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0338. Min Act: -0.0003

Data Index: 851822 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0331. Min Act: -0.0002

Data Index: 939955 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1025309 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0329. Min Act: -0.0004

Data Index: 657259 (C4 (Web Text))

Max Activating Token Index: 1005