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

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

Neuron 3214 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2171. Min Act: -0.0001

Data Index: 1193885 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2186. Min Act: -0.0002

Data Index: 146329 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1782. Min Act: -0.0001

Data Index: 40715 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1847. Min Act: -0.0002

Data Index: 147184 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1845. Min Act: -0.0002

Data Index: 1206161 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1826. Min Act: -0.0002

Data Index: 857562 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1690. Min Act: -0.0002

Data Index: 345022 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1756. Min Act: -0.0002

Data Index: 923442 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1699. Min Act: -0.0001

Data Index: 574134 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1787. Min Act: -0.0002

Data Index: 306256 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1646. Min Act: -0.0002

Data Index: 521928 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1750. Min Act: -0.0002

Data Index: 1156099 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1565. Min Act: -0.0002

Data Index: 734037 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1011172 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1780. Min Act: -0.0002

Data Index: 651024 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1648. Min Act: -0.0001

Data Index: 659338 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1696. Min Act: -0.0001

Data Index: 592520 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1707. Min Act: -0.0002

Data Index: 1141342 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1558. Min Act: -0.0002

Data Index: 769283 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1609. Min Act: -0.0002

Data Index: 70389 (C4 (Web Text))

Max Activating Token Index: 815