Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1383953 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1284. Min Act: -0.0001

Data Index: 268982 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1273. Min Act: -0.0001

Data Index: 810707 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1123367 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1138. Min Act: -0.0001

Data Index: 305817 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1273428 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1333815 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1146. Min Act: -0.0001

Data Index: 326692 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1151. Min Act: -0.0001

Data Index: 64662 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1142. Min Act: -0.0001

Data Index: 281538 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1138. Min Act: -0.0001

Data Index: 819325 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1141. Min Act: -0.0001

Data Index: 27020 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1101. Min Act: -0.0001

Data Index: 381778 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1093. Min Act: -0.0001

Data Index: 655207 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1293043 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1154503 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1102200 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1109. Min Act: -0.0001

Data Index: 235253 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1072. Min Act: -0.0001

Data Index: 676131 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1072891 (C4 (Web Text))

Max Activating Token Index: 655