Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 167 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8875. Min Act: -0.0003

Data Index: 105759 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8551. Min Act: -0.0003

Data Index: 806705 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8539. Min Act: -0.0003

Data Index: 67002 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8765. Min Act: -0.0003

Data Index: 112342 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8409. Min Act: -0.0003

Data Index: 103763 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8162. Min Act: -0.0003

Data Index: 1275089 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8296. Min Act: -0.0003

Data Index: 396146 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7790. Min Act: -0.0003

Data Index: 788480 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8058. Min Act: -0.0003

Data Index: 238378 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7565. Min Act: -0.0003

Data Index: 708071 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8044. Min Act: -0.0003

Data Index: 778139 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8045. Min Act: -0.0003

Data Index: 377187 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7702. Min Act: -0.0003

Data Index: 55720 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7963. Min Act: -0.0003

Data Index: 680671 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7870. Min Act: -0.0003

Data Index: 38731 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7923. Min Act: -0.0003

Data Index: 700433 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8134. Min Act: -0.0003

Data Index: 831128 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7506. Min Act: -0.0003

Data Index: 1025948 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7791. Min Act: -0.0003

Data Index: 123061 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8247. Min Act: -0.0003

Data Index: 1099065 (C4 (Web Text))

Max Activating Token Index: 308