Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3851 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.5076. Min Act: -0.0000

Data Index: 1050095 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.4619. Min Act: -0.0000

Data Index: 30159 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.7145. Min Act: -0.0000

Data Index: 1459791 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.8069. Min Act: -0.0000

Data Index: 902891 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.3178. Min Act: -0.0000

Data Index: 1131590 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.2913. Min Act: -0.0000

Data Index: 1747487 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.2687. Min Act: -0.0000

Data Index: 42022 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.3927. Min Act: -0.0000

Data Index: 1523708 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.2512. Min Act: -0.0000

Data Index: 1193996 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.2525. Min Act: -0.0000

Data Index: 1136216 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.5406. Min Act: -0.0000

Data Index: 1438735 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.4101. Min Act: -0.0000

Data Index: 919489 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.1024. Min Act: -0.0000

Data Index: 594670 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.2330. Min Act: -0.0000

Data Index: 1302552 (The Pile)

Max Activating Token Index: 309

Text #14

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.3808. Min Act: -0.0000

Data Index: 445046 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.2167. Min Act: -0.0000

Data Index: 799691 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.3235. Min Act: -0.0000

Data Index: 1666143 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.1991. Min Act: -0.0000

Data Index: 1292821 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.4780. Min Act: -0.0000

Data Index: 864045 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.1817. Min Act: -0.0000

Data Index: 1482119 (The Pile)

Max Activating Token Index: 28