Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4768 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1935. Min Range: -5.1935

Max Act: 5.1935. Min Act: -0.0000

Data Index: 611848 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.1765. Min Act: -0.0000

Data Index: 788973 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.8029. Min Act: -0.0000

Data Index: 883245 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.6447. Min Act: -0.0000

Data Index: 201601 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.8057. Min Act: -0.0000

Data Index: 124566 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.1903. Min Act: -0.0000

Data Index: 1060697 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.2935. Min Act: -0.0000

Data Index: 555073 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 5.1935. Min Range: -5.1935

Max Act: 2.9698. Min Act: -0.0000

Data Index: 121012 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.2445. Min Act: -0.0000

Data Index: 737711 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.1733. Min Act: -0.0000

Data Index: 1112466 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.1216. Min Act: -0.0000

Data Index: 1022942 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.0943. Min Act: -0.0000

Data Index: 666962 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.0924. Min Act: -0.0000

Data Index: 968946 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.2379. Min Act: -0.0000

Data Index: 244670 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.0255. Min Act: -0.0000

Data Index: 867925 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 5.1935. Min Range: -5.1935

Max Act: 2.9455. Min Act: -0.0000

Data Index: 670129 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.0327. Min Act: -0.0000

Data Index: 60815 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.1703. Min Act: -0.0000

Data Index: 18520 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.0112. Min Act: -0.0000

Data Index: 577446 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 5.1935. Min Range: -5.1935

Max Act: 3.1370. Min Act: -0.0000

Data Index: 904439 (C4 (Web Text))

Max Activating Token Index: 886