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

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

Neuron 2596 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.5658. Min Act: -0.0000

Data Index: 136204 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.3396. Min Act: -0.0000

Data Index: 1143876 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.1998. Min Act: -0.0000

Data Index: 1167775 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.2372. Min Act: -0.0000

Data Index: 1097837 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.2331. Min Act: -0.0000

Data Index: 461641 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 2.5658. Min Range: -2.5658

Max Act: 1.9659. Min Act: -0.0000

Data Index: 99654 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 2.5658. Min Range: -2.5658

Max Act: 1.8794. Min Act: -0.0000

Data Index: 23960 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.0687. Min Act: -0.0000

Data Index: 1300122 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.0089. Min Act: -0.0000

Data Index: 1342845 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.0502. Min Act: -0.0000

Data Index: 19457 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.0705. Min Act: -0.0000

Data Index: 313060 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.0081. Min Act: -0.0000

Data Index: 1097093 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 2.5658. Min Range: -2.5658

Max Act: 1.9916. Min Act: -0.0000

Data Index: 418425 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.0199. Min Act: -0.0000

Data Index: 1116244 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 2.5658. Min Range: -2.5658

Max Act: 1.9589. Min Act: -0.0000

Data Index: 468694 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 2.5658. Min Range: -2.5658

Max Act: 1.9732. Min Act: -0.0000

Data Index: 173444 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.0373. Min Act: -0.0000

Data Index: 1063896 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 2.5658. Min Range: -2.5658

Max Act: 1.9274. Min Act: -0.0000

Data Index: 600800 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 2.5658. Min Range: -2.5658

Max Act: 1.8700. Min Act: -0.0000

Data Index: 344331 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 2.5658. Min Range: -2.5658

Max Act: 2.0199. Min Act: -0.0000

Data Index: 876974 (C4 (Web Text))

Max Activating Token Index: 376