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

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

Neuron 3439 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1287. Min Act: -0.0000

Data Index: 772418 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1355. Min Act: -0.0000

Data Index: 648182 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1180. Min Act: -0.0000

Data Index: 487510 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1169. Min Act: -0.0000

Data Index: 473533 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1118. Min Act: -0.0000

Data Index: 6850 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1053. Min Act: -0.0000

Data Index: 547093 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1085440 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1027. Min Act: -0.0000

Data Index: 568620 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1030. Min Act: -0.0000

Data Index: 890278 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1002899 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1115. Min Act: -0.0000

Data Index: 928400 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0937. Min Act: -0.0000

Data Index: 700706 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1111. Min Act: -0.0000

Data Index: 826843 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1130912 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0916. Min Act: -0.0000

Data Index: 496806 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0946. Min Act: -0.0000

Data Index: 960362 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0911. Min Act: -0.0000

Data Index: 576141 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0937. Min Act: -0.0000

Data Index: 992004 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1309517 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1169182 (C4 (Web Text))

Max Activating Token Index: 289