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

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

Neuron 5495 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1742. Min Range: -1.1742

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1348064 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.1742. Min Range: -1.1742

Max Act: 1.1072. Min Act: -0.0000

Data Index: 222993 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.9319. Min Act: -0.0000

Data Index: 816886 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 1.1742. Min Range: -1.1742

Max Act: 1.0250. Min Act: -0.0000

Data Index: 558661 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8954. Min Act: -0.0000

Data Index: 30379 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.9040. Min Act: -0.0000

Data Index: 880973 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1056775 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8773. Min Act: -0.0000

Data Index: 33079 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8585. Min Act: -0.0000

Data Index: 978806 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1149511 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8297. Min Act: -0.0000

Data Index: 101929 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7545. Min Act: -0.0000

Data Index: 833025 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7622. Min Act: -0.0000

Data Index: 222768 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8148. Min Act: -0.0000

Data Index: 198875 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8417. Min Act: -0.0000

Data Index: 163053 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7542. Min Act: -0.0000

Data Index: 93704 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.9150. Min Act: -0.0000

Data Index: 388022 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.7809. Min Act: -0.0000

Data Index: 86714 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8450. Min Act: -0.0000

Data Index: 136828 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 1.1742. Min Range: -1.1742

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1272324 (C4 (Web Text))

Max Activating Token Index: 816