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

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

Neuron 4699 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1146101 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1088. Min Act: -0.0002

Data Index: 35889 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1045731 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1039. Min Act: -0.0002

Data Index: 261212 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1029. Min Act: -0.0002

Data Index: 665360 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1005265 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1138530 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1000. Min Act: -0.0002

Data Index: 166284 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1077734 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0999. Min Act: -0.0002

Data Index: 430971 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1008. Min Act: -0.0002

Data Index: 799808 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1237260 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0969. Min Act: -0.0002

Data Index: 29468 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0983. Min Act: -0.0002

Data Index: 716269 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1079567 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0969. Min Act: -0.0002

Data Index: 210093 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1209459 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0930. Min Act: -0.0002

Data Index: 817128 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1334299 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1122178 (C4 (Web Text))

Max Activating Token Index: 220