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

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

Neuron 2947 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1079923 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1228040 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.4860. Min Act: 0.0000

Data Index: 1637163 (Python Code)

Max Activating Token Index: 396

Text #3

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.3547. Min Act: -0.0000

Data Index: 661497 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.2255. Min Act: -0.0000

Data Index: 809661 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1015344 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.1839. Min Act: -0.0000

Data Index: 370986 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.2454. Min Act: -0.0000

Data Index: 278617 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1176979 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.2251. Min Act: -0.0000

Data Index: 508354 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.1326. Min Act: -0.0000

Data Index: 551972 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.0695. Min Act: -0.0000

Data Index: 485289 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1438427 (Python Code)

Max Activating Token Index: 883

Text #13

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.1010. Min Act: -0.0000

Data Index: 270305 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.0850. Min Act: -0.0000

Data Index: 827544 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.0193. Min Act: -0.0000

Data Index: 53333 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1368324 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.0773. Min Act: -0.0000

Data Index: 636763 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.0633. Min Act: -0.0000

Data Index: 722025 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.0679. Min Act: 0.0000

Data Index: 1498784 (Python Code)

Max Activating Token Index: 501