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

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

Neuron 3995 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2931. Min Act: -0.0002

Data Index: 708095 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.3031. Min Act: -0.0001

Data Index: 415451 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2979. Min Act: -0.0001

Data Index: 260204 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2890. Min Act: -0.0001

Data Index: 704560 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2711. Min Act: -0.0001

Data Index: 719050 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2591. Min Act: -0.0002

Data Index: 657015 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2845. Min Act: -0.0001

Data Index: 281484 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2807. Min Act: -0.0002

Data Index: 171930 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2515. Min Act: -0.0002

Data Index: 366566 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2752. Min Act: -0.0002

Data Index: 802868 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2435. Min Act: -0.0001

Data Index: 1199074 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2163. Min Act: -0.0002

Data Index: 1276381 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2581. Min Act: -0.0002

Data Index: 900554 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2129. Min Act: -0.0001

Data Index: 303704 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2459. Min Act: -0.0002

Data Index: 1357718 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2324. Min Act: -0.0002

Data Index: 823788 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2781. Min Act: -0.0001

Data Index: 274417 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2170. Min Act: -0.0002

Data Index: 1273722 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2632. Min Act: -0.0002

Data Index: 323497 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1283531 (C4 (Web Text))

Max Activating Token Index: 342