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

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

Neuron 3045 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: 0.2108. Min Range: -0.2108

Max Act: 0.2108. Min Act: -0.0000

Data Index: 74468 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1846. Min Act: -0.0000

Data Index: 61533 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1912. Min Act: -0.0000

Data Index: 163023 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1237312 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1641. Min Act: -0.0000

Data Index: 931404 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1603. Min Act: -0.0000

Data Index: 234208 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1621. Min Act: -0.0000

Data Index: 876887 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1575. Min Act: -0.0000

Data Index: 520475 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1625. Min Act: -0.0000

Data Index: 752304 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1597. Min Act: -0.0000

Data Index: 418415 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1562. Min Act: -0.0000

Data Index: 671422 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1356. Min Act: -0.0000

Data Index: 444545 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1452. Min Act: -0.0000

Data Index: 314631 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1393. Min Act: -0.0000

Data Index: 499756 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1153047 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1080351 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1379. Min Act: -0.0000

Data Index: 710732 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1050222 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1008019 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1403. Min Act: -0.0000

Data Index: 310870 (C4 (Web Text))

Max Activating Token Index: 513