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

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

Neuron 5421 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1073819 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.9106. Min Act: -0.0001

Data Index: 82830 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8722. Min Act: -0.0001

Data Index: 412339 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8717. Min Act: -0.0001

Data Index: 532689 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8217. Min Act: -0.0001

Data Index: 775042 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7960. Min Act: -0.0001

Data Index: 1059205 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7823. Min Act: -0.0001

Data Index: 743695 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8493. Min Act: -0.0001

Data Index: 418911 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7939. Min Act: -0.0001

Data Index: 1157074 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8624. Min Act: -0.0001

Data Index: 192626 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7736. Min Act: -0.0001

Data Index: 132120 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7957. Min Act: -0.0001

Data Index: 1603 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7435. Min Act: -0.0001

Data Index: 909146 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7449. Min Act: -0.0001

Data Index: 1080813 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7084. Min Act: -0.0001

Data Index: 1098921 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7233. Min Act: -0.0001

Data Index: 468267 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1045765 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7221. Min Act: -0.0001

Data Index: 11585 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7447. Min Act: -0.0001

Data Index: 694812 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7182. Min Act: -0.0001

Data Index: 696015 (C4 (Web Text))

Max Activating Token Index: 612