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

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

Neuron 3414 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1028181 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0902. Min Act: -0.0002

Data Index: 702571 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0793. Min Act: -0.0002

Data Index: 319349 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1100233 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0744. Min Act: -0.0002

Data Index: 989774 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0710. Min Act: -0.0002

Data Index: 350108 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1258170 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1357169 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0692. Min Act: -0.0002

Data Index: 939324 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0689. Min Act: -0.0002

Data Index: 769346 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0682. Min Act: -0.0002

Data Index: 133648 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0677. Min Act: -0.0002

Data Index: 456128 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1172485 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0690. Min Act: -0.0002

Data Index: 418039 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1390184 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0674. Min Act: -0.0002

Data Index: 581904 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0666. Min Act: -0.0002

Data Index: 81463 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0657. Min Act: -0.0002

Data Index: 690961 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0670. Min Act: -0.0002

Data Index: 8959 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0644. Min Act: -0.0002

Data Index: 671498 (C4 (Web Text))

Max Activating Token Index: 64