Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2293 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0043. Min Range: -2.0043

Max Act: 2.0043. Min Act: -0.0000

Data Index: 744719 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.8414. Min Act: -0.0000

Data Index: 453067 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.7035. Min Act: -0.0000

Data Index: 896401 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6991. Min Act: -0.0000

Data Index: 377433 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6841. Min Act: -0.0000

Data Index: 1217854 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.5913. Min Act: -0.0000

Data Index: 1300306 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6094. Min Act: -0.0001

Data Index: 604318 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.5222. Min Act: -0.0000

Data Index: 246818 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.5081. Min Act: -0.0000

Data Index: 397314 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.4759. Min Act: -0.0000

Data Index: 952860 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.4941. Min Act: 0.0002

Data Index: 1253632 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.4651. Min Act: -0.0000

Data Index: 909785 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.5377. Min Act: 0.0000

Data Index: 445040 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.4042. Min Act: -0.0000

Data Index: 381472 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.3704. Min Act: -0.0000

Data Index: 650222 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.4052. Min Act: -0.0000

Data Index: 1232738 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.4004. Min Act: -0.0001

Data Index: 176999 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.4408. Min Act: -0.0000

Data Index: 144848 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.3282. Min Act: -0.0000

Data Index: 413846 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.3647. Min Act: 0.0000

Data Index: 830094 (C4 (Web Text))

Max Activating Token Index: 151