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

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

Neuron 2617 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.6225. Min Act: -0.0000

Data Index: 825770 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.2307. Min Act: -0.0000

Data Index: 319226 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.1975. Min Act: -0.0000

Data Index: 177627 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.2807. Min Act: -0.0000

Data Index: 595382 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.2639. Min Act: -0.0000

Data Index: 277004 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.0231. Min Act: -0.0000

Data Index: 1204978 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.3514. Min Act: -0.0000

Data Index: 1351642 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.2497. Min Act: -0.0000

Data Index: 234144 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.2413. Min Act: -0.0000

Data Index: 497716 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.9868. Min Act: -0.0000

Data Index: 633424 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 2.6225. Min Range: -2.6225

Max Act: 2.2039. Min Act: -0.0000

Data Index: 1281345 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.9102. Min Act: -0.0000

Data Index: 564436 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.9956. Min Act: -0.0000

Data Index: 967633 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.9637. Min Act: -0.0000

Data Index: 1008249 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.9529. Min Act: -0.0000

Data Index: 366393 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.9418. Min Act: -0.0000

Data Index: 677625 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.8857. Min Act: -0.0000

Data Index: 419539 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.8879. Min Act: -0.0000

Data Index: 889191 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.8874. Min Act: -0.0000

Data Index: 785227 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 2.6225. Min Range: -2.6225

Max Act: 1.8749. Min Act: -0.0000

Data Index: 931381 (C4 (Web Text))

Max Activating Token Index: 616