Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3811 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5548. Min Act: -0.0001

Data Index: 855409 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4875. Min Act: -0.0001

Data Index: 470673 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4836. Min Act: -0.0001

Data Index: 470285 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4909. Min Act: -0.0001

Data Index: 1123991 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4512. Min Act: -0.0001

Data Index: 73411 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4649. Min Act: -0.0001

Data Index: 1099563 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4515. Min Act: -0.0001

Data Index: 546594 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3929. Min Act: -0.0001

Data Index: 914820 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1291523 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5040. Min Act: -0.0001

Data Index: 1318722 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4268. Min Act: -0.0001

Data Index: 219303 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3382. Min Act: -0.0001

Data Index: 1200173 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4213. Min Act: -0.0001

Data Index: 819375 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4029. Min Act: -0.0001

Data Index: 71002 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3741. Min Act: -0.0001

Data Index: 491459 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4121. Min Act: -0.0001

Data Index: 1187883 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3707. Min Act: -0.0001

Data Index: 1308162 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3611. Min Act: -0.0001

Data Index: 202490 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3732. Min Act: -0.0001

Data Index: 98801 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4057. Min Act: -0.0001

Data Index: 1324701 (C4 (Web Text))

Max Activating Token Index: 134