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

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

Neuron 638 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1319. Min Act: -0.0001

Data Index: 75682 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1294. Min Act: -0.0001

Data Index: 24102 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1257. Min Act: -0.0001

Data Index: 95097 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1357310 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1212. Min Act: -0.0001

Data Index: 77 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1185. Min Act: -0.0001

Data Index: 949043 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1109. Min Act: -0.0001

Data Index: 585749 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1232598 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1085041 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1146366 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1119. Min Act: -0.0001

Data Index: 136268 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1129. Min Act: -0.0001

Data Index: 8049 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1050899 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1116. Min Act: -0.0001

Data Index: 260869 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1107. Min Act: -0.0001

Data Index: 687797 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1155. Min Act: -0.0001

Data Index: 7045 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1072. Min Act: -0.0001

Data Index: 509170 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1124. Min Act: -0.0001

Data Index: 473716 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1304333 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1115. Min Act: -0.0001

Data Index: 356806 (C4 (Web Text))

Max Activating Token Index: 84