Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1700 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.4729. Min Act: -0.0002

Data Index: 879421 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.4402. Min Act: -0.0001

Data Index: 1265485 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.4119. Min Act: -0.0002

Data Index: 1256195 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.4024. Min Act: -0.0002

Data Index: 743106 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3944. Min Act: -0.0002

Data Index: 310060 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3911. Min Act: -0.0002

Data Index: 115960 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3911. Min Act: -0.0002

Data Index: 358248 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3795. Min Act: -0.0001

Data Index: 854204 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3511. Min Act: -0.0001

Data Index: 697045 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3636. Min Act: -0.0002

Data Index: 464947 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3572. Min Act: -0.0002

Data Index: 997944 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3707. Min Act: -0.0002

Data Index: 378629 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3594. Min Act: -0.0001

Data Index: 597962 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3506. Min Act: -0.0001

Data Index: 1122730 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3647. Min Act: -0.0001

Data Index: 306101 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3480. Min Act: -0.0002

Data Index: 213797 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3503. Min Act: -0.0002

Data Index: 40954 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3460. Min Act: -0.0002

Data Index: 636357 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3515. Min Act: -0.0001

Data Index: 28545 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.4729. Min Range: -0.4729

Max Act: 0.3191. Min Act: -0.0002

Data Index: 124376 (C4 (Web Text))

Max Activating Token Index: 846