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

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

Neuron 1895 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1119. Min Range: -1.1119

Max Act: 1.0605. Min Act: -0.0001

Data Index: 447761 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 1.1119. Min Range: -1.1119

Max Act: 1.1119. Min Act: -0.0001

Data Index: 200282 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 1.1119. Min Range: -1.1119

Max Act: 1.0391. Min Act: -0.0001

Data Index: 269417 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 1.1119. Min Range: -1.1119

Max Act: 1.0545. Min Act: -0.0001

Data Index: 694881 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 1.1119. Min Range: -1.1119

Max Act: 1.0150. Min Act: -0.0001

Data Index: 704435 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 1.1119. Min Range: -1.1119

Max Act: 1.0165. Min Act: -0.0001

Data Index: 1132043 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.1119. Min Range: -1.1119

Max Act: 1.0024. Min Act: -0.0001

Data Index: 317461 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9306. Min Act: -0.0001

Data Index: 1101330 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 1.1119. Min Range: -1.1119

Max Act: 1.0722. Min Act: -0.0001

Data Index: 268734 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9741. Min Act: -0.0001

Data Index: 1117458 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9422. Min Act: -0.0001

Data Index: 993122 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9664. Min Act: -0.0001

Data Index: 183823 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9597. Min Act: -0.0001

Data Index: 125398 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9551. Min Act: -0.0001

Data Index: 436666 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9544. Min Act: -0.0001

Data Index: 944125 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9258. Min Act: -0.0001

Data Index: 59727 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9456. Min Act: -0.0001

Data Index: 295487 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9372. Min Act: -0.0001

Data Index: 498999 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9397. Min Act: -0.0001

Data Index: 676288 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9628. Min Act: -0.0001

Data Index: 39174 (C4 (Web Text))

Max Activating Token Index: 485