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

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

Neuron 3974 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1185897 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1211. Min Act: -0.0000

Data Index: 771650 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1295369 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1125526 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1081. Min Act: -0.0000

Data Index: 153271 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1036. Min Act: -0.0000

Data Index: 104607 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1033. Min Act: -0.0000

Data Index: 695903 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1245601 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0992. Min Act: -0.0000

Data Index: 315306 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1023. Min Act: -0.0000

Data Index: 254100 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1335434 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0960. Min Act: -0.0000

Data Index: 814402 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0980. Min Act: -0.0000

Data Index: 88762 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0938. Min Act: -0.0000

Data Index: 501759 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0928. Min Act: -0.0000

Data Index: 785533 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1238546 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0885. Min Act: -0.0000

Data Index: 144545 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0886. Min Act: 0.0000

Data Index: 860281 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1244338 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1112195 (C4 (Web Text))

Max Activating Token Index: 54