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

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

Neuron 4146 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.4750. Min Act: -0.0001

Data Index: 405297 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.4949. Min Act: -0.0001

Data Index: 235370 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.2702. Min Act: -0.0001

Data Index: 1240567 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.0735. Min Act: -0.0001

Data Index: 1303518 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.0528. Min Act: -0.0001

Data Index: 5481 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.0881. Min Act: -0.0001

Data Index: 40315 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.0500. Min Act: -0.0001

Data Index: 869418 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.0850. Min Act: -0.0001

Data Index: 304662 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 1.4949. Min Range: -1.4949

Max Act: 0.8479. Min Act: -0.0001

Data Index: 938269 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.0321. Min Act: -0.0001

Data Index: 744285 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.4949. Min Range: -1.4949

Max Act: 0.9493. Min Act: -0.0001

Data Index: 226989 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 1.4949. Min Range: -1.4949

Max Act: 0.9144. Min Act: -0.0001

Data Index: 761077 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.0371. Min Act: -0.0001

Data Index: 384430 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.4949. Min Range: -1.4949

Max Act: 0.8812. Min Act: -0.0001

Data Index: 800002 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.0246. Min Act: -0.0001

Data Index: 51367 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 1.4949. Min Range: -1.4949

Max Act: 0.9274. Min Act: -0.0001

Data Index: 723896 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.0829. Min Act: -0.0001

Data Index: 792267 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 1.4949. Min Range: -1.4949

Max Act: 0.9072. Min Act: -0.0001

Data Index: 610381 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.4949. Min Range: -1.4949

Max Act: 0.9639. Min Act: -0.0001

Data Index: 1268810 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 1.4949. Min Range: -1.4949

Max Act: 0.8814. Min Act: -0.0001

Data Index: 804329 (C4 (Web Text))

Max Activating Token Index: 42