Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1792 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7765. Min Act: -0.0000

Data Index: 757592 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.8186. Min Act: -0.0000

Data Index: 327617 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1570662 (Python Code)

Max Activating Token Index: 927

Text #3

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1630713 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1417095 (Python Code)

Max Activating Token Index: 934

Text #5

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1587495 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1469956 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1198453 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1411210 (Python Code)

Max Activating Token Index: 974

Text #9

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1493509 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1541914 (Python Code)

Max Activating Token Index: 64

Text #11

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1467557 (Python Code)

Max Activating Token Index: 400

Text #12

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7038. Min Act: -0.0000

Data Index: 604009 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1590545 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1249997 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1520194 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1523405 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1533758 (Python Code)

Max Activating Token Index: 529

Text #18

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1476742 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1505420 (Python Code)

Max Activating Token Index: 325