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

Dataset: The Pile

Neuron 4073 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: 1.4614. Min Range: -1.4614

Max Act: 1.4614. Min Act: -0.0000

Data Index: 207631 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1082664 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1454795 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.3435. Min Act: -0.0000

Data Index: 1992065 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1430370 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1430382 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.0935. Min Act: -0.0000

Data Index: 50586 (The Pile)

Max Activating Token Index: 876

Text #7

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1698197 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1939651 (The Pile)

Max Activating Token Index: 507

Text #9

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1599354 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 1.4614. Min Range: -1.4614

Max Act: 0.9885. Min Act: -0.0000

Data Index: 364320 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.0485. Min Act: -0.0000

Data Index: 697582 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1340343 (The Pile)

Max Activating Token Index: 318

Text #13

Max Range: 1.4614. Min Range: -1.4614

Max Act: 0.9709. Min Act: -0.0000

Data Index: 360490 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.4614. Min Range: -1.4614

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1127439 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 1.4614. Min Range: -1.4614

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1948369 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 1.4614. Min Range: -1.4614

Max Act: 0.9802. Min Act: -0.0000

Data Index: 673543 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 1.4614. Min Range: -1.4614

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1132766 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 1.4614. Min Range: -1.4614

Max Act: 0.9063. Min Act: -0.0000

Data Index: 396763 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 1.4614. Min Range: -1.4614

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1754916 (The Pile)

Max Activating Token Index: 519