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

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

Neuron 3753 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: 5.5918. Min Range: -5.5918

Max Act: 5.5918. Min Act: -0.0000

Data Index: 963843 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 5.5918. Min Range: -5.5918

Max Act: 4.0743. Min Act: -0.0001

Data Index: 937829 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 5.5918. Min Range: -5.5918

Max Act: 4.4356. Min Act: -0.0001

Data Index: 1343975 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 5.5918. Min Range: -5.5918

Max Act: 4.5068. Min Act: -0.0001

Data Index: 1169175 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 5.5918. Min Range: -5.5918

Max Act: 4.3827. Min Act: -0.0001

Data Index: 324459 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 5.5918. Min Range: -5.5918

Max Act: 4.1072. Min Act: -0.0001

Data Index: 634132 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 5.5918. Min Range: -5.5918

Max Act: 4.2809. Min Act: -0.0001

Data Index: 1117275 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 5.5918. Min Range: -5.5918

Max Act: 4.2767. Min Act: -0.0001

Data Index: 542996 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.9943. Min Act: -0.0001

Data Index: 128261 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 5.5918. Min Range: -5.5918

Max Act: 4.0905. Min Act: -0.0001

Data Index: 1095751 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.6555. Min Act: -0.0001

Data Index: 1254006 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.8395. Min Act: -0.0000

Data Index: 305313 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.7623. Min Act: -0.0001

Data Index: 1009524 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.7135. Min Act: -0.0001

Data Index: 502796 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.7506. Min Act: -0.0001

Data Index: 216047 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.6433. Min Act: -0.0001

Data Index: 898565 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.4264. Min Act: -0.0001

Data Index: 899789 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.5477. Min Act: -0.0001

Data Index: 224294 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.5302. Min Act: -0.0001

Data Index: 381940 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 5.5918. Min Range: -5.5918

Max Act: 3.4870. Min Act: -0.0001

Data Index: 1049051 (C4 (Web Text))

Max Activating Token Index: 450