Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2106 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.6498. Min Act: -0.0002

Data Index: 503938 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.5259. Min Act: -0.0002

Data Index: 412000 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.5451. Min Act: -0.0002

Data Index: 545107 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.4402. Min Act: -0.0002

Data Index: 906642 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.5197. Min Act: -0.0002

Data Index: 101676 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.3752. Min Act: -0.0002

Data Index: 693354 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.3580. Min Act: -0.0002

Data Index: 497072 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.2690. Min Act: -0.0002

Data Index: 100289 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.2941. Min Act: -0.0002

Data Index: 1331645 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.4212. Min Act: -0.0002

Data Index: 1134633 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.3052. Min Act: -0.0002

Data Index: 938437 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.3329. Min Act: -0.0002

Data Index: 628380 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.3636. Min Act: -0.0002

Data Index: 15601 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.2820. Min Act: -0.0002

Data Index: 105904 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.3146. Min Act: -0.0002

Data Index: 928150 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.3466. Min Act: -0.0002

Data Index: 1219769 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.3649. Min Act: -0.0002

Data Index: 582763 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.2351. Min Act: -0.0002

Data Index: 1309751 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.2377. Min Act: -0.0002

Data Index: 401481 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.6498. Min Range: -1.6498

Max Act: 1.3340. Min Act: -0.0002

Data Index: 874698 (C4 (Web Text))

Max Activating Token Index: 442