Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2835 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3970. Min Act: -0.0001

Data Index: 749935 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3867. Min Act: -0.0001

Data Index: 250078 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3689. Min Act: -0.0000

Data Index: 151725 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3462. Min Act: -0.0000

Data Index: 277392 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3317. Min Act: -0.0000

Data Index: 222410 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3033. Min Act: -0.0000

Data Index: 443161 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3118. Min Act: -0.0000

Data Index: 187285 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2629. Min Act: -0.0000

Data Index: 629905 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3156. Min Act: -0.0000

Data Index: 746639 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2911. Min Act: -0.0001

Data Index: 814007 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2713. Min Act: -0.0001

Data Index: 220294 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2691. Min Act: -0.0000

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1278448 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2666. Min Act: -0.0000

Data Index: 900802 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2731. Min Act: -0.0000

Data Index: 118536 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2712. Min Act: -0.0000

Data Index: 157849 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2408. Min Act: -0.0000

Data Index: 966932 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2852. Min Act: -0.0001

Data Index: 834665 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1198870 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1210898 (C4 (Web Text))

Max Activating Token Index: 798