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

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

Neuron 3255 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4726. Min Act: -0.0000

Data Index: 786242 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4247. Min Act: -0.0000

Data Index: 135996 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4452. Min Act: -0.0000

Data Index: 234668 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1030127 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3800. Min Act: -0.0000

Data Index: 878138 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1282443 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3518. Min Act: -0.0000

Data Index: 780199 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3710. Min Act: -0.0000

Data Index: 540788 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3823. Min Act: -0.0001

Data Index: 2907 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1271426 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1326985 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3427. Min Act: -0.0000

Data Index: 508715 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3372. Min Act: -0.0000

Data Index: 33081 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3436. Min Act: -0.0001

Data Index: 727326 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3132. Min Act: -0.0000

Data Index: 86650 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3221. Min Act: -0.0000

Data Index: 45470 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3092. Min Act: -0.0001

Data Index: 191759 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3129. Min Act: -0.0001

Data Index: 51395 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3011. Min Act: -0.0001

Data Index: 328333 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2941. Min Act: -0.0001

Data Index: 246841 (C4 (Web Text))

Max Activating Token Index: 222