Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1214 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4823. Min Act: -0.0000

Data Index: 799839 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4062. Min Act: -0.0001

Data Index: 1145744 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4006. Min Act: -0.0001

Data Index: 1352648 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4131. Min Act: -0.0001

Data Index: 157387 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4139. Min Act: -0.0001

Data Index: 401203 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3780. Min Act: -0.0001

Data Index: 249333 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3891. Min Act: -0.0001

Data Index: 1227910 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1054676 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3761. Min Act: -0.0000

Data Index: 284371 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3745. Min Act: -0.0001

Data Index: 1125573 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3482. Min Act: -0.0001

Data Index: 61806 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3611. Min Act: -0.0001

Data Index: 1280631 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3679. Min Act: -0.0001

Data Index: 291807 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2978. Min Act: -0.0001

Data Index: 293546 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3454. Min Act: -0.0001

Data Index: 105817 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1283694 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3507. Min Act: -0.0001

Data Index: 1120916 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3587. Min Act: -0.0001

Data Index: 1038489 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3107. Min Act: -0.0001

Data Index: 184616 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3204. Min Act: -0.0001

Data Index: 847449 (C4 (Web Text))

Max Activating Token Index: 822