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

Dataset: The Pile

Neuron 1158 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0004

Data Index: 1921468 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1078. Min Act: -0.0004

Data Index: 342801 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1069. Min Act: -0.0004

Data Index: 898028 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1061. Min Act: -0.0004

Data Index: 1251993 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1052. Min Act: -0.0004

Data Index: 20290 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1015. Min Act: -0.0004

Data Index: 302443 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0961. Min Act: -0.0004

Data Index: 59195 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1022. Min Act: -0.0004

Data Index: 264664 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1054. Min Act: -0.0004

Data Index: 168637 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0977. Min Act: -0.0004

Data Index: 705660 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0992. Min Act: -0.0004

Data Index: 161325 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0939. Min Act: -0.0004

Data Index: 150680 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0987. Min Act: -0.0004

Data Index: 840422 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0968. Min Act: -0.0004

Data Index: 611466 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0962. Min Act: -0.0004

Data Index: 567261 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0945. Min Act: -0.0004

Data Index: 1380284 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0930. Min Act: -0.0004

Data Index: 273235 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0932. Min Act: -0.0004

Data Index: 740943 (The Pile)

Max Activating Token Index: 238

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0934. Min Act: -0.0004

Data Index: 933289 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0967. Min Act: -0.0004

Data Index: 1854218 (The Pile)

Max Activating Token Index: 437