Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 939 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0050. Min Act: -0.0006

Data Index: 838689 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0049. Min Act: -0.0006

Data Index: 672133 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0050. Min Act: -0.0005

Data Index: 186118 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1274907 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1213401 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0045. Min Act: -0.0006

Data Index: 522718 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1047013 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0044. Min Act: -0.0006

Data Index: 899889 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0006

Data Index: 983728 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0006

Data Index: 1349248 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0044. Min Act: -0.0005

Data Index: 698083 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0005

Data Index: 645717 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0005

Data Index: 1130389 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0005

Data Index: 529439 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0005

Data Index: 631782 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0005

Data Index: 865983 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0006

Data Index: 1020767 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0005

Data Index: 828041 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0006

Data Index: 686990 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0006

Data Index: 1337630 (C4 (Web Text))

Max Activating Token Index: 270