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

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

Neuron 4857 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.7209. Min Act: -0.0000

Data Index: 668136 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.8008. Min Act: -0.0000

Data Index: 124921 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.2955. Min Act: -0.0000

Data Index: 1205102 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.2878. Min Act: -0.0000

Data Index: 713261 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.3894. Min Act: -0.0000

Data Index: 78543 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.4577. Min Act: -0.0000

Data Index: 1196508 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.3130. Min Act: -0.0000

Data Index: 45772 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.4316. Min Act: -0.0000

Data Index: 1311434 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.1183. Min Act: -0.0000

Data Index: 1314879 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.1689. Min Act: -0.0000

Data Index: 144144 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.1509. Min Act: -0.0000

Data Index: 219999 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.1112. Min Act: -0.0000

Data Index: 1083463 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.2252. Min Act: -0.0000

Data Index: 1004627 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.0902. Min Act: -0.0000

Data Index: 17739 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.0834. Min Act: -0.0000

Data Index: 1041905 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.0714. Min Act: -0.0000

Data Index: 42847 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.0538. Min Act: -0.0000

Data Index: 472141 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 2.8008. Min Range: -2.8008

Max Act: 1.9524. Min Act: -0.0000

Data Index: 38115 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 2.8008. Min Range: -2.8008

Max Act: 2.1286. Min Act: -0.0000

Data Index: 397720 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 2.8008. Min Range: -2.8008

Max Act: 1.9980. Min Act: -0.0000

Data Index: 719380 (C4 (Web Text))

Max Activating Token Index: 674