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

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

Neuron 8 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.1527. Min Act: -0.0000

Data Index: 1186475 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.0162. Min Act: -0.0000

Data Index: 429188 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.0618. Min Act: -0.0000

Data Index: 908136 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.0160. Min Act: -0.0000

Data Index: 149100 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.0573. Min Act: -0.0000

Data Index: 758427 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.0209. Min Act: -0.0000

Data Index: 263468 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1351952 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.0268. Min Act: -0.0000

Data Index: 790078 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9856. Min Act: -0.0000

Data Index: 756108 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9862. Min Act: -0.0000

Data Index: 918242 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9944. Min Act: -0.0000

Data Index: 465061 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.0043. Min Act: -0.0000

Data Index: 103754 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1338526 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9676. Min Act: -0.0000

Data Index: 916495 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9410. Min Act: -0.0000

Data Index: 420911 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9123. Min Act: -0.0000

Data Index: 366017 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9686. Min Act: -0.0000

Data Index: 289394 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9714. Min Act: -0.0000

Data Index: 190862 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9902. Min Act: -0.0000

Data Index: 488059 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1291745 (C4 (Web Text))

Max Activating Token Index: 658