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

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

Neuron 2160 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.1889. Min Act: -0.0000

Data Index: 907825 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.2036. Min Act: -0.0000

Data Index: 212887 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.1477. Min Act: -0.0000

Data Index: 719080 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0609. Min Act: -0.0000

Data Index: 694486 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1332361 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0531. Min Act: -0.0000

Data Index: 318759 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9774. Min Act: -0.0000

Data Index: 184846 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0145. Min Act: -0.0000

Data Index: 533907 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0107. Min Act: -0.0000

Data Index: 439328 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9532. Min Act: -0.0000

Data Index: 114257 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9609. Min Act: -0.0000

Data Index: 145402 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1041994 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9276. Min Act: -0.0000

Data Index: 66017 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9469. Min Act: -0.0000

Data Index: 580632 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9630. Min Act: -0.0000

Data Index: 503703 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8934. Min Act: -0.0000

Data Index: 799696 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8907. Min Act: -0.0000

Data Index: 866131 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9009. Min Act: -0.0000

Data Index: 631748 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8718. Min Act: -0.0000

Data Index: 411207 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8945. Min Act: -0.0000

Data Index: 152656 (C4 (Web Text))

Max Activating Token Index: 876