Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8578. Min Range: -2.8578

Max Act: 2.8578. Min Act: -0.0000

Data Index: 213215 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 2.8578. Min Range: -2.8578

Max Act: 2.1617. Min Act: -0.0000

Data Index: 615849 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 2.8578. Min Range: -2.8578

Max Act: 2.2755. Min Act: -0.0000

Data Index: 672130 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 2.8578. Min Range: -2.8578

Max Act: 2.2202. Min Act: -0.0000

Data Index: 318187 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 2.8578. Min Range: -2.8578

Max Act: 2.0005. Min Act: -0.0000

Data Index: 505741 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 2.8578. Min Range: -2.8578

Max Act: 2.1111. Min Act: -0.0000

Data Index: 42041 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 2.8578. Min Range: -2.8578

Max Act: 2.0967. Min Act: -0.0000

Data Index: 1260911 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 2.8578. Min Range: -2.8578

Max Act: 2.0121. Min Act: -0.0000

Data Index: 1064531 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.8961. Min Act: -0.0000

Data Index: 1000734 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.9983. Min Act: -0.0000

Data Index: 555401 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.9994. Min Act: -0.0000

Data Index: 796478 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.8863. Min Act: -0.0000

Data Index: 1176398 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.7545. Min Act: -0.0000

Data Index: 1245044 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.8342. Min Act: -0.0000

Data Index: 193207 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.8899. Min Act: -0.0000

Data Index: 1311424 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.6652. Min Act: -0.0000

Data Index: 719538 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.7043. Min Act: -0.0000

Data Index: 101653 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.8008. Min Act: -0.0000

Data Index: 1266081 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.7025. Min Act: -0.0000

Data Index: 1008680 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 2.8578. Min Range: -2.8578

Max Act: 1.7023. Min Act: -0.0000

Data Index: 748736 (C4 (Web Text))

Max Activating Token Index: 116