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

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

Neuron 1694 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: 0.1224. Min Range: -0.1224

Max Act: 0.1224. Min Act: -0.0002

Data Index: 1549139 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1208. Min Act: -0.0002

Data Index: 1351940 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1168. Min Act: -0.0002

Data Index: 557321 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1163. Min Act: -0.0002

Data Index: 7773 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1148. Min Act: -0.0002

Data Index: 648105 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1383035 (Python Code)

Max Activating Token Index: 452

Text #6

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1134. Min Act: -0.0002

Data Index: 198504 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1247874 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1127. Min Act: -0.0002

Data Index: 973123 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1084. Min Act: -0.0002

Data Index: 36072 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1088. Min Act: -0.0002

Data Index: 497661 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1086. Min Act: -0.0002

Data Index: 1179736 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1054. Min Act: -0.0002

Data Index: 801709 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1403310 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1045. Min Act: -0.0002

Data Index: 786710 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1037. Min Act: -0.0002

Data Index: 764238 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1136074 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1022413 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1309658 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1023. Min Act: -0.0002

Data Index: 380448 (C4 (Web Text))

Max Activating Token Index: 269