Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1070 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0108. Min Act: -0.0003

Data Index: 281903 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1059743 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0100. Min Act: -0.0003

Data Index: 215131 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1410377 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1398665 (Python Code)

Max Activating Token Index: 330

Text #5

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0100. Min Act: -0.0003

Data Index: 294286 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1634836 (Python Code)

Max Activating Token Index: 955

Text #7

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1386098 (Python Code)

Max Activating Token Index: 937

Text #8

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1614769 (Python Code)

Max Activating Token Index: 812

Text #9

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1379537 (Python Code)

Max Activating Token Index: 325

Text #10

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0087. Min Act: -0.0003

Data Index: 108944 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1518732 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0087. Min Act: -0.0004

Data Index: 1505729 (Python Code)

Max Activating Token Index: 628

Text #13

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1619123 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0089. Min Act: -0.0003

Data Index: 1599575 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0087. Min Act: -0.0003

Data Index: 798457 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0086. Min Act: -0.0003

Data Index: 453363 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1192867 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1449634 (Python Code)

Max Activating Token Index: 755

Text #19

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1401021 (Python Code)

Max Activating Token Index: 370