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

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

Neuron 3346 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3129. Min Range: -6.3129

Max Act: 6.3129. Min Act: -0.0000

Data Index: 443268 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 6.3129. Min Range: -6.3129

Max Act: 6.1540. Min Act: -0.0000

Data Index: 1144842 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 6.3129. Min Range: -6.3129

Max Act: 6.2785. Min Act: -0.0000

Data Index: 1094375 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.9486. Min Act: -0.0000

Data Index: 1018980 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.8731. Min Act: -0.0000

Data Index: 456305 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.5581. Min Act: -0.0000

Data Index: 287813 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.5298. Min Act: -0.0000

Data Index: 378985 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.5124. Min Act: -0.0000

Data Index: 367837 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.3699. Min Act: -0.0000

Data Index: 651582 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.4637. Min Act: -0.0000

Data Index: 67397 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.1924. Min Act: -0.0000

Data Index: 940356 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.1636. Min Act: -0.0000

Data Index: 41740 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 6.3129. Min Range: -6.3129

Max Act: 4.8966. Min Act: -0.0000

Data Index: 100821 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 6.3129. Min Range: -6.3129

Max Act: 4.8492. Min Act: -0.0000

Data Index: 355868 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.0231. Min Act: -0.0000

Data Index: 7967 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 6.3129. Min Range: -6.3129

Max Act: 4.9910. Min Act: -0.0000

Data Index: 299031 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 6.3129. Min Range: -6.3129

Max Act: 4.9501. Min Act: -0.0000

Data Index: 140651 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 6.3129. Min Range: -6.3129

Max Act: 5.1054. Min Act: -0.0000

Data Index: 394690 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 6.3129. Min Range: -6.3129

Max Act: 4.9111. Min Act: -0.0000

Data Index: 510414 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 6.3129. Min Range: -6.3129

Max Act: 4.7409. Min Act: -0.0000

Data Index: 1197920 (C4 (Web Text))

Max Activating Token Index: 954