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

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

Neuron 2378 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2450. Min Act: -0.0001

Data Index: 348650 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2315. Min Act: -0.0001

Data Index: 913724 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1070394 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2026. Min Act: -0.0000

Data Index: 275418 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2089. Min Act: -0.0000

Data Index: 977538 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1983. Min Act: -0.0001

Data Index: 714013 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2047. Min Act: -0.0001

Data Index: 380238 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1975. Min Act: -0.0001

Data Index: 490729 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1685. Min Act: -0.0001

Data Index: 972984 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1787. Min Act: -0.0001

Data Index: 579698 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1083782 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1160495 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1742. Min Act: -0.0001

Data Index: 254516 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1088772 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1832. Min Act: -0.0001

Data Index: 661164 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1338356 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1835. Min Act: -0.0001

Data Index: 987641 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1114007 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1865. Min Act: -0.0001

Data Index: 823489 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1792. Min Act: -0.0001

Data Index: 939675 (C4 (Web Text))

Max Activating Token Index: 150