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

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

Neuron 689 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: 0.6999. Min Range: -0.6999

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1160373 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.6531. Min Act: -0.0000

Data Index: 772569 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5733. Min Act: -0.0000

Data Index: 933294 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5806. Min Act: -0.0000

Data Index: 377550 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1639931 (Python Code)

Max Activating Token Index: 981

Text #5

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5817. Min Act: -0.0000

Data Index: 567236 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5791. Min Act: -0.0000

Data Index: 325648 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5532. Min Act: -0.0000

Data Index: 35780 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5694. Min Act: -0.0000

Data Index: 117940 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5524. Min Act: -0.0000

Data Index: 963461 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5677. Min Act: -0.0000

Data Index: 466573 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1096199 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5479. Min Act: -0.0000

Data Index: 32993 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5306. Min Act: -0.0000

Data Index: 877768 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5272. Min Act: -0.0000

Data Index: 733406 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1209782 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5220. Min Act: -0.0000

Data Index: 19213 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1200972 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5358. Min Act: -0.0000

Data Index: 89569 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.6999. Min Range: -0.6999

Max Act: 0.5078. Min Act: -0.0000

Data Index: 699221 (C4 (Web Text))

Max Activating Token Index: 402