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

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

Neuron 1214 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: 0.1577. Min Range: -0.1577

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1300110 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1087668 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1268. Min Act: -0.0000

Data Index: 434782 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1315. Min Act: -0.0000

Data Index: 604799 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1239. Min Act: -0.0000

Data Index: 767413 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1284. Min Act: -0.0000

Data Index: 933707 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1288. Min Act: -0.0000

Data Index: 638931 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1281. Min Act: -0.0000

Data Index: 991331 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1184. Min Act: -0.0000

Data Index: 330004 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1184. Min Act: -0.0001

Data Index: 750499 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1106. Min Act: -0.0000

Data Index: 451458 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1140. Min Act: -0.0000

Data Index: 67393 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1164. Min Act: -0.0001

Data Index: 597160 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1105. Min Act: -0.0001

Data Index: 487244 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1182. Min Act: -0.0000

Data Index: 352000 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1166. Min Act: -0.0000

Data Index: 340341 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1059. Min Act: -0.0000

Data Index: 819341 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1092. Min Act: -0.0000

Data Index: 471070 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1173. Min Act: -0.0001

Data Index: 603458 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1107. Min Act: -0.0000

Data Index: 562472 (C4 (Web Text))

Max Activating Token Index: 111