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

Dataset: The Pile

Neuron 1520 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4750. Min Act: -0.0000

Data Index: 165756 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1301387 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4493. Min Act: 0.0000

Data Index: 555223 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4759. Min Act: -0.0000

Data Index: 807522 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4479. Min Act: 0.0000

Data Index: 1310398 (The Pile)

Max Activating Token Index: 1007

Text #5

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4238. Min Act: -0.0000

Data Index: 454569 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1603752 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1870826 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4282. Min Act: 0.0000

Data Index: 540838 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1552352 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4071. Min Act: 0.0000

Data Index: 608568 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4074. Min Act: 0.0000

Data Index: 1309333 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3874. Min Act: -0.0000

Data Index: 96198 (The Pile)

Max Activating Token Index: 525

Text #13

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1551721 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1883579 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1351917 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3941. Min Act: 0.0000

Data Index: 30474 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1373539 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1263080 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1553601 (The Pile)

Max Activating Token Index: 224