Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 393 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.8611. Min Act: -0.0000

Data Index: 310790 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7583. Min Act: -0.0000

Data Index: 267514 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1204763 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7731. Min Act: -0.0000

Data Index: 890504 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7772. Min Act: -0.0000

Data Index: 37711 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7543. Min Act: -0.0000

Data Index: 308944 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7882. Min Act: -0.0000

Data Index: 796574 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7852. Min Act: -0.0000

Data Index: 938630 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7168. Min Act: -0.0000

Data Index: 936723 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6880. Min Act: 0.0001

Data Index: 1163362 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6796. Min Act: -0.0000

Data Index: 701166 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6818. Min Act: -0.0000

Data Index: 250975 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1011284 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6402. Min Act: -0.0000

Data Index: 609834 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6106. Min Act: -0.0000

Data Index: 278325 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6213. Min Act: -0.0000

Data Index: 18194 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6083. Min Act: -0.0000

Data Index: 145713 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6362. Min Act: -0.0000

Data Index: 265608 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5840. Min Act: -0.0000

Data Index: 797599 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1257960 (C4 (Web Text))

Max Activating Token Index: 315