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

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

Neuron 5859 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.8931. Min Act: -0.0000

Data Index: 197006 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.7985. Min Act: -0.0000

Data Index: 409120 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.7254. Min Act: -0.0000

Data Index: 654219 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.7229. Min Act: -0.0000

Data Index: 917630 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1274026 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.6817. Min Act: -0.0000

Data Index: 23912 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1159822 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.6051. Min Act: -0.0000

Data Index: 235055 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5726. Min Act: -0.0000

Data Index: 148823 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5689. Min Act: -0.0000

Data Index: 786345 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5806. Min Act: -0.0000

Data Index: 358713 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5511. Min Act: -0.0000

Data Index: 484890 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5843. Min Act: -0.0000

Data Index: 748580 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5456. Min Act: -0.0000

Data Index: 827667 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5055. Min Act: -0.0000

Data Index: 10342 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5456. Min Act: -0.0000

Data Index: 276599 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5131. Min Act: -0.0000

Data Index: 9986 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5344. Min Act: -0.0000

Data Index: 767268 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.4928. Min Act: -0.0000

Data Index: 285436 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.8931. Min Range: -0.8931

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1018323 (C4 (Web Text))

Max Activating Token Index: 252