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

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

Neuron 4992 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: 0.6420. Min Range: -0.6420

Max Act: 0.6420. Min Act: -0.0000

Data Index: 703356 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.5578. Min Act: -0.0000

Data Index: 915382 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.5117. Min Act: -0.0000

Data Index: 917379 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1201461 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.5128. Min Act: -0.0000

Data Index: 741088 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.5028. Min Act: -0.0000

Data Index: 410601 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4859. Min Act: -0.0000

Data Index: 264666 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4756. Min Act: -0.0000

Data Index: 40971 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4660. Min Act: -0.0000

Data Index: 881447 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4490. Min Act: -0.0000

Data Index: 854556 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1314493 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4325. Min Act: -0.0000

Data Index: 286986 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4604. Min Act: -0.0000

Data Index: 647990 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4455. Min Act: -0.0000

Data Index: 780190 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4581. Min Act: -0.0000

Data Index: 962597 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1022275 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4378. Min Act: -0.0000

Data Index: 109477 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1148743 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4298. Min Act: -0.0000

Data Index: 478526 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.6420. Min Range: -0.6420

Max Act: 0.4111. Min Act: -0.0000

Data Index: 196357 (C4 (Web Text))

Max Activating Token Index: 934