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

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

Neuron 2275 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: 0.1285. Min Range: -0.1285

Max Act: 0.1285. Min Act: -0.0001

Data Index: 597534 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1242. Min Act: -0.0001

Data Index: 635634 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1142. Min Act: -0.0001

Data Index: 788485 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1137. Min Act: -0.0001

Data Index: 397482 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1164. Min Act: -0.0001

Data Index: 470344 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1124. Min Act: -0.0001

Data Index: 349374 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1154. Min Act: -0.0001

Data Index: 212336 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1184. Min Act: -0.0001

Data Index: 585564 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1140. Min Act: -0.0001

Data Index: 626175 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1115. Min Act: -0.0001

Data Index: 1311717 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1317240 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1108. Min Act: -0.0001

Data Index: 92624 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1134. Min Act: -0.0001

Data Index: 640717 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1083. Min Act: -0.0001

Data Index: 128491 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1105940 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1101. Min Act: -0.0001

Data Index: 1020025 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1093. Min Act: -0.0001

Data Index: 979423 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1085. Min Act: -0.0001

Data Index: 704422 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1089. Min Act: -0.0001

Data Index: 285742 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1331275 (C4 (Web Text))

Max Activating Token Index: 998