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

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

Neuron 5276 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: 1.3107. Min Range: -1.3107

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1205483 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.3107. Min Range: -1.3107

Max Act: 1.3107. Min Act: -0.0000

Data Index: 1000970 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.3107. Min Range: -1.3107

Max Act: 1.0596. Min Act: -0.0000

Data Index: 540622 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1599647 (Python Code)

Max Activating Token Index: 944

Text #4

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.9789. Min Act: -0.0000

Data Index: 539561 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.9713. Min Act: 0.0000

Data Index: 519400 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1477765 (Python Code)

Max Activating Token Index: 954

Text #7

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.9441. Min Act: -0.0000

Data Index: 942630 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.8751. Min Act: -0.0000

Data Index: 684922 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1414872 (Python Code)

Max Activating Token Index: 930

Text #10

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1397241 (Python Code)

Max Activating Token Index: 489

Text #11

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.9212. Min Act: -0.0000

Data Index: 223441 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1091088 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.8234. Min Act: -0.0000

Data Index: 470092 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.8496. Min Act: 0.0000

Data Index: 931280 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.9008. Min Act: 0.0000

Data Index: 1293702 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1198248 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.7971. Min Act: -0.0000

Data Index: 354526 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1644322 (Python Code)

Max Activating Token Index: 296

Text #19

Max Range: 1.3107. Min Range: -1.3107

Max Act: 0.8837. Min Act: -0.0000

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 923