Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3652 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1147514 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1894. Min Act: -0.0000

Data Index: 421984 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1840. Min Act: -0.0000

Data Index: 736699 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1904. Min Act: -0.0000

Data Index: 648938 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1708. Min Act: -0.0001

Data Index: 1238823 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1646. Min Act: -0.0000

Data Index: 919151 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1636. Min Act: -0.0000

Data Index: 178792 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1555. Min Act: -0.0001

Data Index: 149185 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1651. Min Act: -0.0000

Data Index: 226879 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1537. Min Act: -0.0000

Data Index: 169922 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1430. Min Act: -0.0001

Data Index: 816549 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1316959 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1501. Min Act: -0.0000

Data Index: 903439 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1508. Min Act: -0.0000

Data Index: 999151 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1087511 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1388. Min Act: -0.0000

Data Index: 870885 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1407. Min Act: -0.0000

Data Index: 560757 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1366. Min Act: -0.0000

Data Index: 719396 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1373. Min Act: -0.0000

Data Index: 854874 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1279. Min Act: -0.0001

Data Index: 672657 (C4 (Web Text))

Max Activating Token Index: 232