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

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

Neuron 295 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: 0.1289. Min Range: -0.1289

Max Act: 0.1289. Min Act: -0.0002

Data Index: 1095164 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1186. Min Act: -0.0002

Data Index: 363800 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1168. Min Act: -0.0002

Data Index: 400042 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1127. Min Act: -0.0002

Data Index: 593865 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1087. Min Act: -0.0003

Data Index: 40174 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1085. Min Act: -0.0002

Data Index: 492866 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1077. Min Act: -0.0002

Data Index: 193277 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1116605 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1065. Min Act: -0.0002

Data Index: 735610 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1067. Min Act: -0.0002

Data Index: 109347 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1055. Min Act: -0.0002

Data Index: 15559 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1055. Min Act: -0.0002

Data Index: 623501 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1051. Min Act: -0.0002

Data Index: 640415 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1058. Min Act: -0.0002

Data Index: 363714 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1029. Min Act: -0.0002

Data Index: 865627 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1043. Min Act: -0.0002

Data Index: 917364 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1030. Min Act: -0.0002

Data Index: 941950 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1187624 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1019. Min Act: -0.0003

Data Index: 633382 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0992. Min Act: -0.0002

Data Index: 199705 (C4 (Web Text))

Max Activating Token Index: 854