Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2581 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6460. Min Act: -0.0001

Data Index: 928166 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5551. Min Act: -0.0001

Data Index: 834127 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1220968 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4850. Min Act: -0.0001

Data Index: 1184156 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4952. Min Act: -0.0001

Data Index: 314180 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4974. Min Act: -0.0001

Data Index: 905395 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5035. Min Act: -0.0001

Data Index: 201608 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4812. Min Act: -0.0001

Data Index: 1113329 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5108. Min Act: -0.0001

Data Index: 213703 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4931. Min Act: -0.0001

Data Index: 558810 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4910. Min Act: -0.0001

Data Index: 279804 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4905. Min Act: -0.0001

Data Index: 191925 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5076. Min Act: -0.0001

Data Index: 634407 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4870. Min Act: -0.0001

Data Index: 95322 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4672. Min Act: -0.0001

Data Index: 756303 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4697. Min Act: -0.0001

Data Index: 807864 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4819. Min Act: -0.0001

Data Index: 675818 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4785. Min Act: -0.0001

Data Index: 1230148 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4953. Min Act: -0.0001

Data Index: 499567 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.4626. Min Act: -0.0001

Data Index: 217627 (C4 (Web Text))

Max Activating Token Index: 19