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

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

Neuron 4296 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4062. Min Range: -2.4062

Max Act: 2.4062. Min Act: -0.0000

Data Index: 606376 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 2.4062. Min Range: -2.4062

Max Act: 2.1828. Min Act: 0.0001

Data Index: 330749 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 2.4062. Min Range: -2.4062

Max Act: 2.0717. Min Act: -0.0000

Data Index: 167997 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 2.4062. Min Range: -2.4062

Max Act: 2.0346. Min Act: -0.0000

Data Index: 168181 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.9963. Min Act: -0.0000

Data Index: 545292 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.8770. Min Act: -0.0000

Data Index: 443124 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.8260. Min Act: 0.0000

Data Index: 1225335 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.8006. Min Act: 0.0000

Data Index: 762126 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.7873. Min Act: -0.0000

Data Index: 1097579 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.7579. Min Act: -0.0000

Data Index: 851893 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1115414 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.7312. Min Act: 0.0000

Data Index: 215024 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.7263. Min Act: -0.0000

Data Index: 905760 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.7092. Min Act: -0.0000

Data Index: 436010 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.7015. Min Act: -0.0000

Data Index: 34258 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.6610. Min Act: 0.0000

Data Index: 1106120 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.5424. Min Act: 0.0001

Data Index: 41402 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.6227. Min Act: -0.0000

Data Index: 95888 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.6176. Min Act: 0.0001

Data Index: 695031 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 2.4062. Min Range: -2.4062

Max Act: 1.6064. Min Act: -0.0000

Data Index: 842275 (C4 (Web Text))

Max Activating Token Index: 834