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

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

Neuron 2600 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.7059. Min Act: -0.0001

Data Index: 131204 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.7327. Min Act: -0.0001

Data Index: 840208 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.7551. Min Act: -0.0001

Data Index: 1049036 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.6289. Min Act: -0.0001

Data Index: 183902 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.7787. Min Act: -0.0001

Data Index: 1005488 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.6737. Min Act: -0.0001

Data Index: 670112 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.6316. Min Act: -0.0001

Data Index: 524005 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.7164. Min Act: -0.0001

Data Index: 1006361 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.4849. Min Act: -0.0001

Data Index: 5710 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.6227. Min Act: -0.0001

Data Index: 623902 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.5627. Min Act: -0.0001

Data Index: 319938 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.5039. Min Act: -0.0001

Data Index: 813841 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.5498. Min Act: -0.0001

Data Index: 1251470 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.4146. Min Act: -0.0001

Data Index: 539486 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.2347. Min Act: -0.0001

Data Index: 449684 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.4238. Min Act: -0.0001

Data Index: 599355 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.3801. Min Act: -0.0001

Data Index: 398059 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.3294. Min Act: -0.0001

Data Index: 155915 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.3628. Min Act: -0.0001

Data Index: 195847 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 1.7787. Min Range: -1.7787

Max Act: 1.4720. Min Act: -0.0001

Data Index: 67480 (C4 (Web Text))

Max Activating Token Index: 834