Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 605 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1105. Min Act: -0.0002

Data Index: 787575 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1057. Min Act: -0.0001

Data Index: 18232 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1135. Min Act: -0.0002

Data Index: 430914 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1176936 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0979. Min Act: -0.0002

Data Index: 167998 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1208299 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0995. Min Act: -0.0002

Data Index: 315263 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0954. Min Act: -0.0002

Data Index: 118536 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0984. Min Act: -0.0002

Data Index: 177012 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0964. Min Act: -0.0002

Data Index: 973892 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0961. Min Act: -0.0002

Data Index: 758669 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1243613 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0935. Min Act: -0.0002

Data Index: 950728 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0941. Min Act: -0.0002

Data Index: 663523 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0941. Min Act: -0.0001

Data Index: 445459 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0915. Min Act: -0.0002

Data Index: 546608 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0924. Min Act: -0.0001

Data Index: 671245 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1098247 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0903. Min Act: -0.0002

Data Index: 352278 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0920. Min Act: -0.0002

Data Index: 248003 (C4 (Web Text))

Max Activating Token Index: 271