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

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

Neuron 5109 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1161. Min Act: -0.0002

Data Index: 369671 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1008301 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1351089 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1039. Min Act: -0.0002

Data Index: 57780 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0929. Min Act: -0.0002

Data Index: 568847 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1026. Min Act: -0.0002

Data Index: 122616 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1019. Min Act: -0.0002

Data Index: 394537 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1102808 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0935. Min Act: -0.0002

Data Index: 380774 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0931. Min Act: -0.0002

Data Index: 259844 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1137104 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0921. Min Act: -0.0002

Data Index: 150110 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1356144 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0972. Min Act: -0.0002

Data Index: 315573 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1074. Min Act: -0.0002

Data Index: 257779 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1296779 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0860. Min Act: -0.0002

Data Index: 948971 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0855. Min Act: -0.0002

Data Index: 121887 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0795. Min Act: -0.0002

Data Index: 229022 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0987. Min Act: -0.0002

Data Index: 948608 (C4 (Web Text))

Max Activating Token Index: 787