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

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

Neuron 1918 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: 0.3848. Min Range: -0.3848

Max Act: 0.3764. Min Act: -0.0000

Data Index: 536127 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3694. Min Act: -0.0000

Data Index: 738544 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3848. Min Act: -0.0000

Data Index: 24970 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3600. Min Act: -0.0000

Data Index: 535601 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3339. Min Act: -0.0000

Data Index: 63282 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3229. Min Act: -0.0000

Data Index: 274966 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3043. Min Act: -0.0000

Data Index: 889364 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3109. Min Act: -0.0000

Data Index: 625911 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3154. Min Act: -0.0000

Data Index: 160603 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3043. Min Act: -0.0000

Data Index: 756364 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3027. Min Act: -0.0000

Data Index: 527437 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1141281 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1082444 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2592. Min Act: -0.0000

Data Index: 83073 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1328388 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1060725 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2661. Min Act: -0.0000

Data Index: 967166 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2839. Min Act: -0.0000

Data Index: 794233 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2803. Min Act: -0.0000

Data Index: 771857 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2667. Min Act: -0.0000

Data Index: 96509 (C4 (Web Text))

Max Activating Token Index: 799