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

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

Neuron 1084 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1249. Min Act: -0.0000

Data Index: 889334 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1634504 (Python Code)

Max Activating Token Index: 367

Text #2

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1215. Min Act: -0.0000

Data Index: 687878 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1217. Min Act: -0.0000

Data Index: 261924 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1159. Min Act: -0.0001

Data Index: 7475 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1163. Min Act: -0.0001

Data Index: 98417 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1202307 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1096. Min Act: -0.0001

Data Index: 422869 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1172. Min Act: -0.0000

Data Index: 814898 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1291068 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1081. Min Act: -0.0000

Data Index: 509029 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1179369 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1077. Min Act: -0.0000

Data Index: 162750 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1077. Min Act: -0.0000

Data Index: 598627 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1611254 (Python Code)

Max Activating Token Index: 216

Text #15

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1105. Min Act: -0.0001

Data Index: 800845 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1287083 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1024280 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0979. Min Act: -0.0001

Data Index: 817271 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0965. Min Act: -0.0000

Data Index: 633498 (C4 (Web Text))

Max Activating Token Index: 79