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

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

Neuron 2366 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: 0.2576. Min Range: -0.2576

Max Act: 0.2576. Min Act: 0.0002

Data Index: 151920 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2525. Min Act: -0.0000

Data Index: 860520 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2292. Min Act: 0.0000

Data Index: 960241 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2226. Min Act: -0.0000

Data Index: 643393 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2111. Min Act: -0.0000

Data Index: 98120 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2094. Min Act: -0.0000

Data Index: 408501 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2072. Min Act: -0.0000

Data Index: 237965 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2148. Min Act: -0.0000

Data Index: 756176 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1050966 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2066. Min Act: -0.0000

Data Index: 656793 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1184805 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1953. Min Act: -0.0000

Data Index: 70196 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1994. Min Act: -0.0000

Data Index: 297953 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1880. Min Act: -0.0000

Data Index: 841821 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1806. Min Act: -0.0000

Data Index: 52158 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1868. Min Act: -0.0000

Data Index: 55736 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1851. Min Act: -0.0000

Data Index: 235523 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1852. Min Act: -0.0000

Data Index: 156873 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1915. Min Act: -0.0000

Data Index: 468960 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1033545 (C4 (Web Text))

Max Activating Token Index: 609