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

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

Neuron 1305 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1366. Min Act: -0.0000

Data Index: 310214 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1130310 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1285. Min Act: -0.0000

Data Index: 661894 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1284. Min Act: -0.0001

Data Index: 315983 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1193. Min Act: 0.0000

Data Index: 164337 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1159. Min Act: -0.0001

Data Index: 676944 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1280. Min Act: -0.0001

Data Index: 950841 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1144. Min Act: -0.0000

Data Index: 102247 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1163. Min Act: -0.0000

Data Index: 258528 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1165. Min Act: -0.0001

Data Index: 218237 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1189. Min Act: -0.0001

Data Index: 152929 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1108. Min Act: -0.0000

Data Index: 565331 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1210163 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1090. Min Act: -0.0001

Data Index: 946001 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1146. Min Act: -0.0001

Data Index: 140098 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1037. Min Act: -0.0001

Data Index: 215019 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1027. Min Act: -0.0000

Data Index: 185758 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1259403 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1122. Min Act: -0.0000

Data Index: 459483 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1074. Min Act: -0.0000

Data Index: 793506 (C4 (Web Text))

Max Activating Token Index: 244