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

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

Neuron 3107 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0995. Min Range: -1.0995

Max Act: 1.0995. Min Act: -0.0001

Data Index: 792637 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 1.0995. Min Range: -1.0995

Max Act: 1.0833. Min Act: -0.0001

Data Index: 789714 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 1.0995. Min Range: -1.0995

Max Act: 1.0229. Min Act: -0.0000

Data Index: 580281 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9290. Min Act: -0.0000

Data Index: 443951 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9461. Min Act: -0.0001

Data Index: 594905 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9805. Min Act: -0.0001

Data Index: 933917 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9635. Min Act: -0.0000

Data Index: 214686 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1142338 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8490. Min Act: -0.0001

Data Index: 1019228 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9589. Min Act: -0.0001

Data Index: 602386 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9217. Min Act: -0.0000

Data Index: 121150 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9003. Min Act: -0.0000

Data Index: 338059 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8796. Min Act: -0.0001

Data Index: 436233 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8651. Min Act: -0.0001

Data Index: 1009823 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9236. Min Act: -0.0000

Data Index: 598144 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8263. Min Act: -0.0001

Data Index: 1259408 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8154. Min Act: -0.0000

Data Index: 914103 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8905. Min Act: -0.0001

Data Index: 12587 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8900. Min Act: -0.0001

Data Index: 749548 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8637. Min Act: -0.0001

Data Index: 187793 (C4 (Web Text))

Max Activating Token Index: 600