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

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

Neuron 4069 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.4584. Min Act: -0.0000

Data Index: 1372297 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.5736. Min Act: -0.0000

Data Index: 1423639 (Python Code)

Max Activating Token Index: 717

Text #2

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.8091. Min Act: -0.0001

Data Index: 949110 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.3956. Min Act: -0.0000

Data Index: 1506702 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.5094. Min Act: -0.0000

Data Index: 1649884 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.4609. Min Act: -0.0000

Data Index: 1607818 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.3375. Min Act: -0.0001

Data Index: 233466 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.4117. Min Act: -0.0000

Data Index: 1421804 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.3848. Min Act: -0.0000

Data Index: 268243 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.3689. Min Act: -0.0000

Data Index: 1448273 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.3607. Min Act: -0.0000

Data Index: 1579341 (Python Code)

Max Activating Token Index: 485

Text #11

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.2392. Min Act: -0.0001

Data Index: 72470 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.2392. Min Act: -0.0000

Data Index: 1594028 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.2260. Min Act: -0.0001

Data Index: 942672 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 2.8091. Min Range: -2.8091

Max Act: 1.9994. Min Act: -0.0001

Data Index: 376067 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.1907. Min Act: -0.0000

Data Index: 1603289 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.3056. Min Act: -0.0000

Data Index: 1376852 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.4187. Min Act: -0.0000

Data Index: 1444610 (Python Code)

Max Activating Token Index: 170

Text #18

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.1687. Min Act: -0.0000

Data Index: 246967 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 2.8091. Min Range: -2.8091

Max Act: 2.2731. Min Act: -0.0000

Data Index: 1577458 (Python Code)

Max Activating Token Index: 361