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

Dataset: The Pile

Neuron 2820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.8436. Min Act: -0.0000

Data Index: 922924 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1031822 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.8223. Min Act: -0.0000

Data Index: 500229 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7955. Min Act: -0.0000

Data Index: 552232 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1666258 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1651224 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7773. Min Act: -0.0000

Data Index: 739216 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7958. Min Act: -0.0000

Data Index: 339736 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7487. Min Act: -0.0000

Data Index: 811974 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7622. Min Act: -0.0000

Data Index: 579730 (The Pile)

Max Activating Token Index: 724

Text #10

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7293. Min Act: -0.0000

Data Index: 547011 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6962. Min Act: -0.0000

Data Index: 530316 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1500252 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6475. Min Act: -0.0000

Data Index: 271565 (The Pile)

Max Activating Token Index: 161

Text #14

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7120. Min Act: -0.0000

Data Index: 33588 (The Pile)

Max Activating Token Index: 904

Text #15

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6612. Min Act: -0.0000

Data Index: 56158 (The Pile)

Max Activating Token Index: 692

Text #16

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6770. Min Act: -0.0000

Data Index: 869808 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1525690 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1559285 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6526. Min Act: -0.0000

Data Index: 939911 (The Pile)

Max Activating Token Index: 498