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

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

Neuron 3008 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2136. Min Range: -1.2136

Max Act: 1.1164. Min Act: -0.0001

Data Index: 307662 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.2136. Min Range: -1.2136

Max Act: 1.2136. Min Act: -0.0001

Data Index: 273816 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.8592. Min Act: -0.0001

Data Index: 588827 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1279976 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.8687. Min Act: -0.0000

Data Index: 974822 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.9605. Min Act: -0.0001

Data Index: 906819 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.9604. Min Act: -0.0001

Data Index: 530544 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.9696. Min Act: -0.0001

Data Index: 758837 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.8896. Min Act: -0.0001

Data Index: 718245 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.8133. Min Act: -0.0001

Data Index: 1013109 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.8346. Min Act: -0.0001

Data Index: 220087 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.8795. Min Act: -0.0001

Data Index: 1307934 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.8839. Min Act: -0.0001

Data Index: 815146 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.7916. Min Act: -0.0001

Data Index: 187828 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.7720. Min Act: -0.0001

Data Index: 224401 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.7977. Min Act: -0.0001

Data Index: 1187347 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.8283. Min Act: -0.0000

Data Index: 560306 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.8629. Min Act: -0.0001

Data Index: 674472 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.7967. Min Act: -0.0001

Data Index: 740757 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 1.2136. Min Range: -1.2136

Max Act: 0.7778. Min Act: -0.0001

Data Index: 280877 (C4 (Web Text))

Max Activating Token Index: 637