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

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

Neuron 34 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2134. Min Act: -0.0001

Data Index: 233942 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2796. Min Act: -0.0001

Data Index: 92227 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.5106. Min Act: -0.0001

Data Index: 396983 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2212. Min Act: -0.0001

Data Index: 631761 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2144. Min Act: -0.0001

Data Index: 318533 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0421. Min Act: -0.0001

Data Index: 565260 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1837. Min Act: -0.0001

Data Index: 1163244 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0798. Min Act: -0.0001

Data Index: 1329433 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2714. Min Act: -0.0001

Data Index: 116562 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1382. Min Act: -0.0001

Data Index: 841989 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1366. Min Act: -0.0001

Data Index: 69503 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1756. Min Act: -0.0001

Data Index: 251727 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0499. Min Act: -0.0001

Data Index: 836761 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2769. Min Act: -0.0001

Data Index: 1057067 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1126. Min Act: -0.0001

Data Index: 230853 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0282. Min Act: -0.0001

Data Index: 132009 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0951. Min Act: -0.0001

Data Index: 920659 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.5106. Min Range: -1.5106

Max Act: 0.8234. Min Act: -0.0001

Data Index: 112014 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 1.5106. Min Range: -1.5106

Max Act: 0.9051. Min Act: -0.0001

Data Index: 654060 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 1.5106. Min Range: -1.5106

Max Act: 0.8772. Min Act: -0.0001

Data Index: 31645 (C4 (Web Text))

Max Activating Token Index: 857