Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 459 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1561. Min Act: -0.0003

Data Index: 283066 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1482. Min Act: -0.0003

Data Index: 1085135 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1361. Min Act: -0.0003

Data Index: 209358 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1300. Min Act: -0.0003

Data Index: 202543 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1225. Min Act: -0.0003

Data Index: 538249 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1264. Min Act: -0.0003

Data Index: 1261337 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1210. Min Act: -0.0003

Data Index: 50575 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1252. Min Act: -0.0003

Data Index: 277587 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1140. Min Act: -0.0003

Data Index: 89621 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1163. Min Act: -0.0003

Data Index: 1349897 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1165. Min Act: -0.0003

Data Index: 621724 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1099. Min Act: -0.0003

Data Index: 1236916 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1213. Min Act: -0.0003

Data Index: 459636 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1125. Min Act: -0.0003

Data Index: 1213159 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1044. Min Act: -0.0003

Data Index: 466840 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1095. Min Act: -0.0003

Data Index: 977402 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1054. Min Act: -0.0003

Data Index: 1227998 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1033. Min Act: -0.0003

Data Index: 1014570 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1106. Min Act: -0.0003

Data Index: 519862 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1030. Min Act: -0.0003

Data Index: 541087 (C4 (Web Text))

Max Activating Token Index: 599