Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3461 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.6755. Min Act: -0.0000

Data Index: 420877 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.6291. Min Act: 0.0001

Data Index: 559736 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.5692. Min Act: -0.0000

Data Index: 16781 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.5707. Min Act: -0.0000

Data Index: 228745 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.6908. Min Act: -0.0001

Data Index: 747958 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.5519. Min Act: -0.0000

Data Index: 229015 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.5061. Min Act: -0.0000

Data Index: 228999 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.6120. Min Act: -0.0000

Data Index: 769499 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.4619. Min Act: -0.0000

Data Index: 839414 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.4509. Min Act: -0.0000

Data Index: 182190 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.3038. Min Act: -0.0000

Data Index: 938913 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.4322. Min Act: -0.0000

Data Index: 1309912 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1112780 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.2696. Min Act: -0.0000

Data Index: 167611 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.3928. Min Act: -0.0001

Data Index: 1334970 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.1553. Min Act: -0.0001

Data Index: 227213 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.3697. Min Act: -0.0001

Data Index: 732194 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.4836. Min Act: -0.0001

Data Index: 315766 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.3504. Min Act: -0.0001

Data Index: 562195 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 2.6908. Min Range: -2.6908

Max Act: 2.3262. Min Act: -0.0000

Data Index: 1207517 (C4 (Web Text))

Max Activating Token Index: 639