Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 404 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 7.1496. Min Range: -7.1496

Max Act: 7.1496. Min Act: -0.0000

Data Index: 1270528 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 7.1496. Min Range: -7.1496

Max Act: 6.7224. Min Act: -0.0000

Data Index: 562952 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 7.1496. Min Range: -7.1496

Max Act: 6.0320. Min Act: -0.0000

Data Index: 842170 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.9214. Min Act: -0.0000

Data Index: 440871 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 7.1496. Min Range: -7.1496

Max Act: 5.0924. Min Act: -0.0000

Data Index: 1299920 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 7.1496. Min Range: -7.1496

Max Act: 5.2613. Min Act: -0.0000

Data Index: 1254722 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.2912. Min Act: -0.0000

Data Index: 462979 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 7.1496. Min Range: -7.1496

Max Act: 5.1864. Min Act: -0.0000

Data Index: 1167756 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.7070. Min Act: -0.0000

Data Index: 599223 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 7.1496. Min Range: -7.1496

Max Act: 3.9666. Min Act: -0.0000

Data Index: 44778 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.0826. Min Act: -0.0000

Data Index: 313166 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.6129. Min Act: -0.0000

Data Index: 360351 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.4579. Min Act: -0.0000

Data Index: 879138 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.2447. Min Act: -0.0000

Data Index: 177475 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.2399. Min Act: -0.0000

Data Index: 781217 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.0485. Min Act: -0.0000

Data Index: 983873 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.3237. Min Act: -0.0000

Data Index: 634708 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.2820. Min Act: -0.0000

Data Index: 454544 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.0918. Min Act: -0.0000

Data Index: 1342864 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 7.1496. Min Range: -7.1496

Max Act: 4.0824. Min Act: -0.0000

Data Index: 313364 (C4 (Web Text))

Max Activating Token Index: 304