Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1249 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1671. Min Act: -0.0003

Data Index: 1271376 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1380. Min Act: -0.0004

Data Index: 665225 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1251. Min Act: -0.0003

Data Index: 182908 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1197. Min Act: -0.0003

Data Index: 36738 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1129. Min Act: -0.0004

Data Index: 338665 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1303. Min Act: -0.0003

Data Index: 1213539 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1157. Min Act: -0.0003

Data Index: 306842 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1022. Min Act: -0.0003

Data Index: 654944 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1098. Min Act: -0.0003

Data Index: 768076 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1055. Min Act: -0.0003

Data Index: 1035714 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1030. Min Act: -0.0003

Data Index: 528684 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1098. Min Act: -0.0003

Data Index: 735291 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1019. Min Act: -0.0004

Data Index: 1136528 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1051. Min Act: -0.0003

Data Index: 801376 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1012. Min Act: -0.0003

Data Index: 782941 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1047. Min Act: -0.0003

Data Index: 404783 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1011. Min Act: -0.0003

Data Index: 387577 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1027. Min Act: -0.0003

Data Index: 732971 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1031. Min Act: -0.0003

Data Index: 352417 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1029. Min Act: -0.0003

Data Index: 121845 (C4 (Web Text))

Max Activating Token Index: 493