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

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

Neuron 188 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5602. Min Act: 0.0000

Data Index: 1234715 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5736. Min Act: -0.0000

Data Index: 673597 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.3430. Min Act: -0.0000

Data Index: 71492 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4156. Min Act: -0.0000

Data Index: 999767 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4205. Min Act: -0.0000

Data Index: 800597 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2852. Min Act: 0.0000

Data Index: 90252 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2915. Min Act: 0.0000

Data Index: 1002124 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2417. Min Act: -0.0000

Data Index: 118924 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1177767 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2998. Min Act: -0.0000

Data Index: 850814 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2193. Min Act: 0.0000

Data Index: 664740 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2109. Min Act: -0.0000

Data Index: 146159 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2060. Min Act: -0.0000

Data Index: 816056 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.1435. Min Act: 0.0000

Data Index: 240811 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.1392. Min Act: -0.0000

Data Index: 493977 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1060822 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1096149 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.1208. Min Act: -0.0000

Data Index: 830087 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.1939. Min Act: -0.0000

Data Index: 576550 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1300396 (C4 (Web Text))

Max Activating Token Index: 199