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

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

Neuron 2940 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6889. Min Act: -0.0000

Data Index: 538889 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1267938 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1113657 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.4454. Min Act: 0.0000

Data Index: 538108 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.4284. Min Act: -0.0000

Data Index: 713391 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.4037. Min Act: -0.0000

Data Index: 937055 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3767. Min Act: -0.0000

Data Index: 43865 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1167183 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.4054. Min Act: -0.0000

Data Index: 372646 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3865. Min Act: -0.0001

Data Index: 557099 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1033377 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3762. Min Act: 0.0000

Data Index: 658564 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3505. Min Act: -0.0000

Data Index: 126310 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1293247 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1285499 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3685. Min Act: -0.0001

Data Index: 1263594 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3552. Min Act: -0.0000

Data Index: 229994 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3462. Min Act: -0.0001

Data Index: 1314716 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3441. Min Act: -0.0000

Data Index: 494429 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.3281. Min Act: -0.0001

Data Index: 367388 (C4 (Web Text))

Max Activating Token Index: 757