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

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

Neuron 768 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.2100. Min Act: -0.0000

Data Index: 88973 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1674. Min Act: -0.0000

Data Index: 650911 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1358558 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1307. Min Act: -0.0000

Data Index: 764291 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1196. Min Act: -0.0000

Data Index: 597851 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1237370 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1022. Min Act: -0.0000

Data Index: 58041 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1179. Min Act: -0.0000

Data Index: 801411 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1065. Min Act: -0.0000

Data Index: 223003 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1009. Min Act: -0.0000

Data Index: 112123 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1030. Min Act: -0.0000

Data Index: 145062 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1097. Min Act: -0.0000

Data Index: 242095 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1150. Min Act: -0.0000

Data Index: 162499 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.0925. Min Act: -0.0000

Data Index: 200376 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1327448 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1053. Min Act: -0.0000

Data Index: 887822 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.0870. Min Act: -0.0000

Data Index: 483972 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1037. Min Act: -0.0000

Data Index: 111607 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1002. Min Act: -0.0000

Data Index: 935068 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.0837. Min Act: -0.0000

Data Index: 506256 (C4 (Web Text))

Max Activating Token Index: 873