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

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

Neuron 3423 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0239. Min Range: -4.0239

Max Act: 4.0239. Min Act: -0.0001

Data Index: 885409 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.8455. Min Act: -0.0001

Data Index: 102160 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.4973. Min Act: -0.0001

Data Index: 220907 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.4607. Min Act: -0.0001

Data Index: 288399 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.7685. Min Act: -0.0001

Data Index: 1262963 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.5696. Min Act: -0.0001

Data Index: 573709 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.2550. Min Act: -0.0001

Data Index: 1285439 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.3813. Min Act: -0.0001

Data Index: 179336 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.1085. Min Act: -0.0001

Data Index: 1262049 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.1760. Min Act: -0.0001

Data Index: 917084 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.1798. Min Act: -0.0000

Data Index: 687489 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.1714. Min Act: -0.0001

Data Index: 765796 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 4.0239. Min Range: -4.0239

Max Act: 2.9980. Min Act: -0.0001

Data Index: 331618 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.2866. Min Act: -0.0001

Data Index: 581288 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.1120. Min Act: -0.0001

Data Index: 535374 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 4.0239. Min Range: -4.0239

Max Act: 2.9456. Min Act: -0.0001

Data Index: 1181911 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 4.0239. Min Range: -4.0239

Max Act: 2.7886. Min Act: -0.0001

Data Index: 1076175 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 4.0239. Min Range: -4.0239

Max Act: 2.8827. Min Act: -0.0001

Data Index: 548629 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 4.0239. Min Range: -4.0239

Max Act: 3.0546. Min Act: -0.0001

Data Index: 946360 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 4.0239. Min Range: -4.0239

Max Act: 2.8436. Min Act: -0.0001

Data Index: 765181 (C4 (Web Text))

Max Activating Token Index: 451