Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3752 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3892. Min Act: -0.0000

Data Index: 156769 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1001948 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1262813 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3303. Min Act: -0.0000

Data Index: 7494 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1192638 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1258262 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3255. Min Act: -0.0000

Data Index: 438188 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1132221 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3193. Min Act: -0.0000

Data Index: 43858 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3150. Min Act: -0.0000

Data Index: 635666 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3219. Min Act: -0.0000

Data Index: 760865 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3171. Min Act: -0.0000

Data Index: 852249 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3186. Min Act: -0.0000

Data Index: 44716 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3165. Min Act: -0.0000

Data Index: 154034 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1024588 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3265. Min Act: -0.0000

Data Index: 670690 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1010772 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3072. Min Act: -0.0000

Data Index: 351788 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3144. Min Act: -0.0000

Data Index: 862001 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1340941 (C4 (Web Text))

Max Activating Token Index: 827