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

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

Neuron 2582 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1310. Min Range: -2.1310

Max Act: 2.0718. Min Act: -0.0000

Data Index: 1237618 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 2.1310. Min Range: -2.1310

Max Act: 2.0162. Min Act: -0.0000

Data Index: 291477 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 2.1310. Min Range: -2.1310

Max Act: 2.1310. Min Act: -0.0000

Data Index: 1030104 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.8951. Min Act: -0.0000

Data Index: 1171026 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.8946. Min Act: -0.0000

Data Index: 627194 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.8744. Min Act: -0.0000

Data Index: 235951 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.7793. Min Act: -0.0000

Data Index: 161568 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.8023. Min Act: -0.0000

Data Index: 1248331 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.7309. Min Act: -0.0000

Data Index: 673222 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1081429 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.5036. Min Act: -0.0000

Data Index: 927758 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.7038. Min Act: -0.0000

Data Index: 211221 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.6072. Min Act: -0.0000

Data Index: 522892 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1167821 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.5751. Min Act: -0.0000

Data Index: 836848 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.6847. Min Act: -0.0000

Data Index: 952461 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.3650. Min Act: -0.0000

Data Index: 690386 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.6246. Min Act: -0.0000

Data Index: 488729 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.6198. Min Act: -0.0000

Data Index: 1118526 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 2.1310. Min Range: -2.1310

Max Act: 1.5113. Min Act: -0.0000

Data Index: 1022569 (C4 (Web Text))

Max Activating Token Index: 368