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

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

Neuron 976 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.5980. Min Act: -0.0000

Data Index: 500526 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.4649. Min Act: -0.0000

Data Index: 448546 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.4099. Min Act: -0.0000

Data Index: 1264581 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.3930. Min Act: -0.0000

Data Index: 1217283 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.4927. Min Act: -0.0000

Data Index: 1038502 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.1789. Min Act: -0.0000

Data Index: 1066131 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.5950. Min Act: -0.0000

Data Index: 493480 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.5717. Min Act: -0.0000

Data Index: 9274 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.1301. Min Act: -0.0000

Data Index: 535329 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.1468. Min Act: -0.0000

Data Index: 1287772 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.2633. Min Act: -0.0000

Data Index: 61434 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.1626. Min Act: -0.0000

Data Index: 828086 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.0337. Min Act: -0.0000

Data Index: 459990 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.6027. Min Act: -0.0000

Data Index: 371903 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.2943. Min Act: -0.0000

Data Index: 997531 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 9.6027. Min Range: -9.6027

Max Act: 8.9384. Min Act: -0.0000

Data Index: 607389 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.1013. Min Act: -0.0000

Data Index: 1331912 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 9.6027. Min Range: -9.6027

Max Act: 9.0390. Min Act: -0.0000

Data Index: 1226144 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 9.6027. Min Range: -9.6027

Max Act: 8.8977. Min Act: -0.0000

Data Index: 835066 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 9.6027. Min Range: -9.6027

Max Act: 8.9625. Min Act: -0.0000

Data Index: 129453 (C4 (Web Text))

Max Activating Token Index: 322