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

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

Neuron 5156 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.7428. Min Act: -0.0000

Data Index: 940926 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.4639. Min Act: -0.0000

Data Index: 110408 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.4689. Min Act: -0.0000

Data Index: 879179 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.1310. Min Act: -0.0000

Data Index: 545303 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.0514. Min Act: -0.0000

Data Index: 436563 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.0465. Min Act: -0.0000

Data Index: 636221 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.0369. Min Act: -0.0000

Data Index: 1224906 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.0150. Min Act: -0.0000

Data Index: 911234 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.9722. Min Act: -0.0000

Data Index: 836042 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.0184. Min Act: -0.0000

Data Index: 726053 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.9690. Min Act: -0.0000

Data Index: 234943 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.9676. Min Act: -0.0000

Data Index: 1326876 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.7379. Min Act: -0.0000

Data Index: 663848 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.9375. Min Act: -0.0000

Data Index: 456797 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 2.7428. Min Range: -2.7428

Max Act: 2.0318. Min Act: -0.0000

Data Index: 695940 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.8814. Min Act: -0.0000

Data Index: 244660 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.7633. Min Act: -0.0000

Data Index: 17086 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.7735. Min Act: -0.0000

Data Index: 19590 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.8545. Min Act: -0.0000

Data Index: 285163 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 2.7428. Min Range: -2.7428

Max Act: 1.7344. Min Act: -0.0000

Data Index: 43635 (C4 (Web Text))

Max Activating Token Index: 138