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

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

Neuron 3078 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1278889 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0521. Min Act: -0.0000

Data Index: 881580 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.1029. Min Act: -0.0000

Data Index: 562846 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1260594 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0935. Min Act: -0.0000

Data Index: 21678 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0218. Min Act: -0.0000

Data Index: 833747 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9979. Min Act: -0.0000

Data Index: 234058 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9792. Min Act: -0.0000

Data Index: 227807 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9702. Min Act: -0.0000

Data Index: 995461 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0196. Min Act: -0.0000

Data Index: 466347 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0776. Min Act: -0.0000

Data Index: 115345 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9569. Min Act: -0.0000

Data Index: 665330 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8776. Min Act: -0.0000

Data Index: 268891 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9217. Min Act: -0.0000

Data Index: 452017 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8372. Min Act: -0.0000

Data Index: 730015 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8375. Min Act: -0.0000

Data Index: 403980 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1012451 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8093. Min Act: -0.0000

Data Index: 145704 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8111. Min Act: -0.0000

Data Index: 671059 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8572. Min Act: -0.0000

Data Index: 436071 (C4 (Web Text))

Max Activating Token Index: 963