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

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

Neuron 1196 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3657. Min Range: -2.3657

Max Act: 2.3657. Min Act: -0.0000

Data Index: 808747 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.7835. Min Act: -0.0000

Data Index: 491809 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.8902. Min Act: -0.0000

Data Index: 1272788 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.7729. Min Act: -0.0000

Data Index: 416676 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1014160 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.6876. Min Act: -0.0000

Data Index: 480574 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.5759. Min Act: -0.0000

Data Index: 535132 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.6507. Min Act: -0.0000

Data Index: 553300 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.6490. Min Act: -0.0000

Data Index: 25816 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.5642. Min Act: -0.0000

Data Index: 449386 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.6297. Min Act: -0.0000

Data Index: 278803 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.6228. Min Act: -0.0000

Data Index: 847962 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.6096. Min Act: -0.0000

Data Index: 668800 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.5373. Min Act: -0.0000

Data Index: 990045 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.6165. Min Act: -0.0000

Data Index: 615858 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.5729. Min Act: -0.0000

Data Index: 932998 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.4777. Min Act: -0.0000

Data Index: 418764 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.5447. Min Act: -0.0000

Data Index: 532130 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.4493. Min Act: -0.0000

Data Index: 1315540 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 2.3657. Min Range: -2.3657

Max Act: 1.5071. Min Act: -0.0000

Data Index: 1239463 (C4 (Web Text))

Max Activating Token Index: 416