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

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

Neuron 1618 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.5109. Min Act: -0.0000

Data Index: 48566 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4392. Min Act: -0.0000

Data Index: 955127 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1241451 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4207. Min Act: -0.0000

Data Index: 568449 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3994. Min Act: -0.0000

Data Index: 57433 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3908. Min Act: -0.0000

Data Index: 50268 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4173. Min Act: -0.0000

Data Index: 836651 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4152. Min Act: -0.0000

Data Index: 582154 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3994. Min Act: -0.0000

Data Index: 707738 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4079. Min Act: -0.0000

Data Index: 356638 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4076. Min Act: -0.0000

Data Index: 437017 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3922. Min Act: -0.0000

Data Index: 167500 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3771. Min Act: -0.0000

Data Index: 129058 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1042255 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4026. Min Act: -0.0000

Data Index: 943504 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1251440 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1316424 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3683. Min Act: -0.0000

Data Index: 98829 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3681. Min Act: -0.0000

Data Index: 927060 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3735. Min Act: -0.0000

Data Index: 818491 (C4 (Web Text))

Max Activating Token Index: 74