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

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

Neuron 374 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0418. Min Act: -0.0002

Data Index: 386366 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0350. Min Act: -0.0001

Data Index: 687483 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1201915 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0344. Min Act: -0.0002

Data Index: 767725 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0344. Min Act: -0.0002

Data Index: 372612 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0343. Min Act: -0.0002

Data Index: 763630 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0333. Min Act: -0.0001

Data Index: 533596 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0322. Min Act: -0.0002

Data Index: 147572 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1170049 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1177419 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1313848 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1047186 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0300. Min Act: -0.0002

Data Index: 350481 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1027033 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1211302 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0297. Min Act: -0.0001

Data Index: 851572 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0296. Min Act: -0.0002

Data Index: 165455 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1299959 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0286. Min Act: -0.0002

Data Index: 151574 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0280. Min Act: -0.0002

Data Index: 842573 (C4 (Web Text))

Max Activating Token Index: 1007