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

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

Neuron 249 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: 0.7999. Min Range: -0.7999

Max Act: 0.7873. Min Act: -0.0000

Data Index: 808018 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7999. Min Act: -0.0000

Data Index: 346859 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7591. Min Act: -0.0000

Data Index: 848803 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7176. Min Act: -0.0000

Data Index: 100920 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1012324 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7143. Min Act: -0.0000

Data Index: 261459 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7077. Min Act: -0.0000

Data Index: 939526 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7796. Min Act: -0.0000

Data Index: 621399 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6168. Min Act: -0.0000

Data Index: 599566 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6884. Min Act: -0.0000

Data Index: 398492 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1307433 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1221788 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6679. Min Act: -0.0000

Data Index: 323570 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6292. Min Act: -0.0000

Data Index: 934295 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6771. Min Act: -0.0000

Data Index: 698797 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6345. Min Act: -0.0000

Data Index: 728209 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6749. Min Act: -0.0000

Data Index: 435582 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6695. Min Act: -0.0000

Data Index: 426807 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1246636 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1314029 (C4 (Web Text))

Max Activating Token Index: 90