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

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

Neuron 4919 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: 1.1885. Min Range: -1.1885

Max Act: 1.1885. Min Act: -0.0000

Data Index: 835261 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 1.1885. Min Range: -1.1885

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1120769 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.9702. Min Act: 0.0000

Data Index: 339255 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1065714 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8958. Min Act: -0.0000

Data Index: 616706 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.9187. Min Act: -0.0000

Data Index: 928769 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1058599 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1021501 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1349711 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.7865. Min Act: -0.0000

Data Index: 223653 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8567. Min Act: -0.0000

Data Index: 773559 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8151. Min Act: -0.0000

Data Index: 939350 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8604. Min Act: -0.0000

Data Index: 41753 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8476. Min Act: -0.0000

Data Index: 313124 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8351. Min Act: -0.0000

Data Index: 465952 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.7888. Min Act: -0.0000

Data Index: 763077 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1274727 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.7795. Min Act: -0.0000

Data Index: 583954 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.7574. Min Act: -0.0000

Data Index: 471589 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.1885. Min Range: -1.1885

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1181338 (C4 (Web Text))

Max Activating Token Index: 405