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

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

Neuron 2935 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: 1.1111. Min Range: -1.1111

Max Act: 1.0248. Min Act: -0.0001

Data Index: 1077296 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 1.1111. Min Range: -1.1111

Max Act: 1.0378. Min Act: -0.0002

Data Index: 363225 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 1.1111. Min Range: -1.1111

Max Act: 1.1087. Min Act: -0.0001

Data Index: 468531 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.1111. Min Range: -1.1111

Max Act: 1.1111. Min Act: -0.0001

Data Index: 979796 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9881. Min Act: -0.0002

Data Index: 642412 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9478. Min Act: -0.0002

Data Index: 888703 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9497. Min Act: -0.0001

Data Index: 1062478 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9256. Min Act: -0.0002

Data Index: 1200017 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.8766. Min Act: -0.0002

Data Index: 577544 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.8547. Min Act: -0.0001

Data Index: 1303836 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9809. Min Act: -0.0002

Data Index: 1044271 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9934. Min Act: -0.0002

Data Index: 89947 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9410. Min Act: -0.0002

Data Index: 1212874 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9358. Min Act: -0.0002

Data Index: 776309 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.6948. Min Act: -0.0001

Data Index: 1166912 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9123. Min Act: -0.0002

Data Index: 229266 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9222. Min Act: -0.0002

Data Index: 549690 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9807. Min Act: -0.0002

Data Index: 1257546 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.8710. Min Act: -0.0001

Data Index: 697586 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.8200. Min Act: -0.0002

Data Index: 801920 (C4 (Web Text))

Max Activating Token Index: 609