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

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

Neuron 45 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0985. Min Act: -0.0001

Data Index: 550091 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.2653. Min Act: -0.0001

Data Index: 1296899 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0844. Min Act: -0.0001

Data Index: 86936 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0249. Min Act: -0.0001

Data Index: 1112474 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0595. Min Act: -0.0001

Data Index: 1151949 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0378. Min Act: -0.0001

Data Index: 79565 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0381. Min Act: -0.0001

Data Index: 861107 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9472. Min Act: -0.0001

Data Index: 1186883 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9626. Min Act: -0.0001

Data Index: 940786 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0435. Min Act: -0.0001

Data Index: 848404 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0027. Min Act: -0.0001

Data Index: 135836 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9228. Min Act: -0.0001

Data Index: 799213 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9136. Min Act: -0.0001

Data Index: 479600 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9303. Min Act: -0.0001

Data Index: 149134 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9170. Min Act: -0.0001

Data Index: 761866 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8977. Min Act: -0.0001

Data Index: 1298070 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9748. Min Act: -0.0001

Data Index: 38373 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9017. Min Act: -0.0001

Data Index: 819861 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0115. Min Act: -0.0001

Data Index: 511670 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9441. Min Act: -0.0001

Data Index: 105348 (C4 (Web Text))

Max Activating Token Index: 712