Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1888 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0005

Data Index: 1198932 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0297. Min Act: -0.0005

Data Index: 1534189 (Python Code)

Max Activating Token Index: 492

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0294. Min Act: -0.0005

Data Index: 1609919 (Python Code)

Max Activating Token Index: 532

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0303. Min Act: -0.0005

Data Index: 1107475 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0295. Min Act: -0.0005

Data Index: 1545091 (Python Code)

Max Activating Token Index: 667

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0290. Min Act: -0.0005

Data Index: 988342 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0277. Min Act: -0.0005

Data Index: 1575287 (Python Code)

Max Activating Token Index: 770

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0285. Min Act: -0.0005

Data Index: 520522 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0290. Min Act: -0.0005

Data Index: 1467653 (Python Code)

Max Activating Token Index: 403

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0284. Min Act: -0.0005

Data Index: 539435 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0272. Min Act: -0.0005

Data Index: 1144465 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0289. Min Act: -0.0005

Data Index: 107318 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0280. Min Act: -0.0005

Data Index: 123968 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0306. Min Act: -0.0005

Data Index: 710173 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0280. Min Act: -0.0005

Data Index: 1279752 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1152433 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0276. Min Act: -0.0005

Data Index: 369958 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0269. Min Act: -0.0005

Data Index: 1454109 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0277. Min Act: -0.0005

Data Index: 239271 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0269. Min Act: -0.0005

Data Index: 1358593 (C4 (Web Text))

Max Activating Token Index: 197