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

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

Neuron 4047 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4820. Min Range: -1.4820

Max Act: 1.4820. Min Act: -0.0000

Data Index: 326701 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 1.4820. Min Range: -1.4820

Max Act: 1.2519. Min Act: -0.0000

Data Index: 405403 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 1.4820. Min Range: -1.4820

Max Act: 1.1030. Min Act: -0.0000

Data Index: 319926 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.4820. Min Range: -1.4820

Max Act: 1.0714. Min Act: -0.0000

Data Index: 202760 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1077616 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.9958. Min Act: -0.0000

Data Index: 222599 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1140003 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 1.4820. Min Range: -1.4820

Max Act: 1.0202. Min Act: -0.0000

Data Index: 634106 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.9226. Min Act: -0.0000

Data Index: 535691 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.9707. Min Act: -0.0000

Data Index: 69847 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.9063. Min Act: -0.0000

Data Index: 814372 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1190550 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.8662. Min Act: -0.0000

Data Index: 899142 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1323102 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1306096 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.8812. Min Act: -0.0000

Data Index: 195014 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1140032 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1253605 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1104326 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 1.4820. Min Range: -1.4820

Max Act: 0.8601. Min Act: -0.0000

Data Index: 35496 (C4 (Web Text))

Max Activating Token Index: 524