Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 924 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1062. Min Act: -0.0001

Data Index: 55844 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0877. Min Act: -0.0001

Data Index: 222328 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0851. Min Act: -0.0001

Data Index: 470406 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0835. Min Act: -0.0001

Data Index: 547822 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0812. Min Act: -0.0002

Data Index: 448293 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0813. Min Act: -0.0002

Data Index: 562579 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0827. Min Act: -0.0002

Data Index: 558121 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0813. Min Act: -0.0002

Data Index: 362713 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0842. Min Act: -0.0002

Data Index: 363845 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0834. Min Act: -0.0001

Data Index: 293805 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1051498 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0786. Min Act: -0.0002

Data Index: 443385 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1354371 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0785. Min Act: -0.0002

Data Index: 151141 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0802. Min Act: -0.0001

Data Index: 912021 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0764. Min Act: -0.0001

Data Index: 905711 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0767. Min Act: -0.0001

Data Index: 276639 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0760. Min Act: -0.0002

Data Index: 815063 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1105209 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0750. Min Act: -0.0001

Data Index: 301159 (C4 (Web Text))

Max Activating Token Index: 322