Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2920 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1268. Min Act: -0.0002

Data Index: 1099188 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1222492 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1207. Min Act: -0.0002

Data Index: 616338 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1187. Min Act: -0.0002

Data Index: 335910 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1108. Min Act: -0.0002

Data Index: 347334 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1237503 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1159443 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1342129 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1078246 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1043. Min Act: -0.0002

Data Index: 763512 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1046. Min Act: -0.0002

Data Index: 600552 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1046. Min Act: -0.0002

Data Index: 879846 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1022. Min Act: -0.0002

Data Index: 499115 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1086. Min Act: -0.0002

Data Index: 345919 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0996. Min Act: -0.0002

Data Index: 500473 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1039. Min Act: -0.0002

Data Index: 605966 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0995. Min Act: -0.0002

Data Index: 227432 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1274772 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0996. Min Act: -0.0002

Data Index: 470056 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0988. Min Act: -0.0002

Data Index: 605621 (C4 (Web Text))

Max Activating Token Index: 351