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

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

Neuron 4954 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.9258. Min Act: -0.0000

Data Index: 788672 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.9345. Min Act: -0.0000

Data Index: 620978 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1324798 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7748. Min Act: -0.0000

Data Index: 404241 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.8021. Min Act: -0.0000

Data Index: 585338 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1187049 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.8087. Min Act: -0.0000

Data Index: 87530 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7344. Min Act: -0.0000

Data Index: 637062 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7732. Min Act: -0.0000

Data Index: 464412 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7408. Min Act: -0.0000

Data Index: 555753 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7758. Min Act: -0.0000

Data Index: 729906 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7749. Min Act: -0.0000

Data Index: 342849 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7252. Min Act: -0.0000

Data Index: 311714 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7178. Min Act: -0.0000

Data Index: 793164 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.6875. Min Act: -0.0000

Data Index: 623435 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7216. Min Act: -0.0000

Data Index: 120983 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.6765. Min Act: -0.0000

Data Index: 227409 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7144. Min Act: -0.0000

Data Index: 202484 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7096. Min Act: -0.0000

Data Index: 571665 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7255. Min Act: -0.0000

Data Index: 324729 (C4 (Web Text))

Max Activating Token Index: 646