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

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

Neuron 1204 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: 0.0100. Min Range: -0.0100

Max Act: 0.0100. Min Act: -0.0006

Data Index: 760718 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0093. Min Act: -0.0006

Data Index: 511630 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1022948 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0081. Min Act: -0.0006

Data Index: 296928 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0079. Min Act: -0.0006

Data Index: 134502 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1084405 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1044962 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1149088 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0072. Min Act: -0.0006

Data Index: 770516 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0069. Min Act: -0.0007

Data Index: 173029 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0068. Min Act: -0.0006

Data Index: 119367 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0068. Min Act: -0.0006

Data Index: 736186 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0064. Min Act: -0.0005

Data Index: 869911 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0065. Min Act: -0.0006

Data Index: 817482 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0063. Min Act: -0.0006

Data Index: 101079 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0065. Min Act: -0.0006

Data Index: 522701 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0064. Min Act: -0.0006

Data Index: 184492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1054482 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0062. Min Act: -0.0006

Data Index: 916781 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1071061 (C4 (Web Text))

Max Activating Token Index: 139