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

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

Neuron 4336 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.8870. Min Act: -0.0000

Data Index: 326702 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6762. Min Act: -0.0000

Data Index: 996441 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4931. Min Act: -0.0000

Data Index: 54092 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4838. Min Act: -0.0000

Data Index: 127237 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1296752 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4674. Min Act: -0.0000

Data Index: 783064 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4638. Min Act: -0.0000

Data Index: 95279 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4628. Min Act: -0.0000

Data Index: 75852 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4565. Min Act: -0.0000

Data Index: 272948 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1059601 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4581. Min Act: -0.0000

Data Index: 159635 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4609. Min Act: -0.0000

Data Index: 170826 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1214243 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4235. Min Act: -0.0000

Data Index: 343220 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.3924. Min Act: -0.0000

Data Index: 504097 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4226. Min Act: -0.0000

Data Index: 696847 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.3849. Min Act: -0.0000

Data Index: 453814 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4004. Min Act: -0.0000

Data Index: 841950 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.3873. Min Act: -0.0000

Data Index: 1033830 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1177583 (C4 (Web Text))

Max Activating Token Index: 288