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

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

Neuron 704 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1869. Min Act: -0.0001

Data Index: 213125 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1408513 (Python Code)

Max Activating Token Index: 210

Text #2

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1403660 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1589466 (Python Code)

Max Activating Token Index: 889

Text #4

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1162335 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1527629 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1551247 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1305412 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1151. Min Act: -0.0000

Data Index: 311377 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1482603 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1115. Min Act: -0.0001

Data Index: 1415836 (Python Code)

Max Activating Token Index: 215

Text #11

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1647830 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1585891 (Python Code)

Max Activating Token Index: 582

Text #13

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1617630 (Python Code)

Max Activating Token Index: 534

Text #14

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1580334 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1162694 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1047. Min Act: -0.0001

Data Index: 596154 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1131. Min Act: -0.0001

Data Index: 823882 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1516466 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1098. Min Act: -0.0001

Data Index: 113896 (C4 (Web Text))

Max Activating Token Index: 343