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

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

Neuron 2379 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6635. Min Range: -4.6635

Max Act: 4.6112. Min Act: -0.0000

Data Index: 45153 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 4.6635. Min Range: -4.6635

Max Act: 4.5867. Min Act: -0.0000

Data Index: 666332 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 4.6635. Min Range: -4.6635

Max Act: 4.6635. Min Act: -0.0000

Data Index: 216320 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 4.6635. Min Range: -4.6635

Max Act: 4.4084. Min Act: -0.0000

Data Index: 114646 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 4.6635. Min Range: -4.6635

Max Act: 4.0157. Min Act: -0.0000

Data Index: 898858 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 4.6635. Min Range: -4.6635

Max Act: 4.1108. Min Act: -0.0000

Data Index: 771449 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.7352. Min Act: -0.0000

Data Index: 1255347 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 4.6635. Min Range: -4.6635

Max Act: 4.1833. Min Act: -0.0000

Data Index: 338568 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.8308. Min Act: -0.0000

Data Index: 250299 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.7503. Min Act: -0.0000

Data Index: 430945 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.5776. Min Act: -0.0000

Data Index: 756269 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.5705. Min Act: -0.0000

Data Index: 627601 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.5507. Min Act: -0.0000

Data Index: 289167 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.6883. Min Act: -0.0000

Data Index: 84348 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.8791. Min Act: -0.0000

Data Index: 569653 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.5924. Min Act: -0.0000

Data Index: 637352 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.5849. Min Act: -0.0000

Data Index: 382480 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.5457. Min Act: -0.0000

Data Index: 1059123 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.5772. Min Act: -0.0000

Data Index: 1198585 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 4.6635. Min Range: -4.6635

Max Act: 3.4926. Min Act: -0.0000

Data Index: 896149 (C4 (Web Text))

Max Activating Token Index: 211