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

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

Neuron 3185 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1301574 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3241. Min Act: -0.0000

Data Index: 923404 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3034. Min Act: -0.0000

Data Index: 486823 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3149. Min Act: -0.0000

Data Index: 42348 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1232576 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2910. Min Act: -0.0000

Data Index: 818419 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2889. Min Act: -0.0000

Data Index: 796849 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2677. Min Act: -0.0000

Data Index: 300223 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2926. Min Act: -0.0000

Data Index: 782861 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2730. Min Act: -0.0000

Data Index: 333291 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2668. Min Act: -0.0000

Data Index: 13549 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2655. Min Act: -0.0000

Data Index: 189960 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1468364 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2628. Min Act: -0.0000

Data Index: 859339 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1433705 (Python Code)

Max Activating Token Index: 652

Text #15

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1459212 (Python Code)

Max Activating Token Index: 348

Text #16

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1560546 (Python Code)

Max Activating Token Index: 434

Text #17

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2667. Min Act: -0.0000

Data Index: 367437 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2568. Min Act: -0.0000

Data Index: 322820 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2475. Min Act: -0.0000

Data Index: 348474 (C4 (Web Text))

Max Activating Token Index: 668