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

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

Neuron 2994 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: 0.1197. Min Range: -0.1197

Max Act: 0.1155. Min Act: -0.0003

Data Index: 1400336 (Python Code)

Max Activating Token Index: 408

Text #1

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1160. Min Act: -0.0003

Data Index: 1461106 (Python Code)

Max Activating Token Index: 98

Text #2

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1182. Min Act: -0.0003

Data Index: 1642910 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1093. Min Act: -0.0003

Data Index: 1432992 (Python Code)

Max Activating Token Index: 202

Text #4

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1116. Min Act: -0.0003

Data Index: 194903 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1100. Min Act: -0.0003

Data Index: 496080 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1623396 (Python Code)

Max Activating Token Index: 839

Text #7

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1137. Min Act: -0.0003

Data Index: 1516345 (Python Code)

Max Activating Token Index: 274

Text #8

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1129. Min Act: -0.0003

Data Index: 1490529 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1080. Min Act: -0.0003

Data Index: 1508971 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1045. Min Act: -0.0003

Data Index: 1512415 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1197. Min Act: -0.0003

Data Index: 540296 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1085. Min Act: -0.0003

Data Index: 1450322 (Python Code)

Max Activating Token Index: 288

Text #13

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1159. Min Act: -0.0003

Data Index: 1428741 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1073. Min Act: -0.0003

Data Index: 1582271 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1104. Min Act: -0.0003

Data Index: 1552992 (Python Code)

Max Activating Token Index: 228

Text #16

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1141. Min Act: -0.0003

Data Index: 1655404 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1098. Min Act: -0.0003

Data Index: 1469319 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1051. Min Act: -0.0003

Data Index: 1590079 (Python Code)

Max Activating Token Index: 279

Text #19

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1052. Min Act: -0.0003

Data Index: 1458520 (Python Code)

Max Activating Token Index: 374