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

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

Neuron 3673 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.3113. Min Act: -0.0000

Data Index: 527273 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1182435 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2022. Min Act: -0.0000

Data Index: 801866 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1883. Min Act: -0.0000

Data Index: 773419 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2337. Min Act: -0.0000

Data Index: 782869 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1852. Min Act: -0.0000

Data Index: 899698 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1649. Min Act: -0.0000

Data Index: 30370 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1768. Min Act: -0.0000

Data Index: 974383 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1589234 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1455. Min Act: -0.0000

Data Index: 719066 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1801. Min Act: -0.0000

Data Index: 465155 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1465. Min Act: -0.0000

Data Index: 767812 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1500. Min Act: -0.0000

Data Index: 371253 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1402. Min Act: -0.0000

Data Index: 782233 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1149924 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1134214 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1372. Min Act: -0.0000

Data Index: 406018 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1416. Min Act: -0.0000

Data Index: 6780 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1556. Min Act: -0.0000

Data Index: 511956 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1230847 (C4 (Web Text))

Max Activating Token Index: 114