Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2573 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2574. Min Range: -3.2574

Max Act: 3.2574. Min Act: -0.0000

Data Index: 745093 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.1951. Min Act: -0.0001

Data Index: 643840 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.4451. Min Act: -0.0000

Data Index: 461735 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.3823. Min Act: -0.0000

Data Index: 967129 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.3041. Min Act: -0.0001

Data Index: 378354 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.0989. Min Act: -0.0001

Data Index: 697800 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.1776. Min Act: -0.0001

Data Index: 746244 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.1272. Min Act: -0.0001

Data Index: 1066877 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.0335. Min Act: -0.0001

Data Index: 220443 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.1039. Min Act: -0.0001

Data Index: 326924 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 3.2574. Min Range: -3.2574

Max Act: 2.0081. Min Act: -0.0001

Data Index: 505762 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 3.2574. Min Range: -3.2574

Max Act: 1.9028. Min Act: -0.0001

Data Index: 509302 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 3.2574. Min Range: -3.2574

Max Act: 1.9820. Min Act: -0.0000

Data Index: 248610 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 3.2574. Min Range: -3.2574

Max Act: 1.9752. Min Act: -0.0001

Data Index: 580117 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 3.2574. Min Range: -3.2574

Max Act: 1.9481. Min Act: -0.0001

Data Index: 1157744 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 3.2574. Min Range: -3.2574

Max Act: 1.9269. Min Act: -0.0001

Data Index: 288650 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 3.2574. Min Range: -3.2574

Max Act: 1.8162. Min Act: -0.0001

Data Index: 385463 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 3.2574. Min Range: -3.2574

Max Act: 1.9267. Min Act: -0.0001

Data Index: 945765 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 3.2574. Min Range: -3.2574

Max Act: 1.9153. Min Act: -0.0001

Data Index: 974817 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 3.2574. Min Range: -3.2574

Max Act: 1.8031. Min Act: -0.0001

Data Index: 366355 (C4 (Web Text))

Max Activating Token Index: 309