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

Dataset: The Pile

Neuron 3996 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1679777 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.8368. Min Act: 0.0000

Data Index: 312138 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.7873. Min Act: -0.0000

Data Index: 816555 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1093331 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.8184. Min Act: -0.0000

Data Index: 917654 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1155282 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1075569 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6772. Min Act: -0.0000

Data Index: 778661 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6816. Min Act: -0.0000

Data Index: 565884 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6719. Min Act: -0.0000

Data Index: 717707 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.7157. Min Act: -0.0000

Data Index: 327300 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6703. Min Act: 0.0000

Data Index: 1786026 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6333. Min Act: 0.0000

Data Index: 509427 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1521649 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1659628 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6797. Min Act: -0.0000

Data Index: 719660 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1449540 (The Pile)

Max Activating Token Index: 438

Text #17

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6532. Min Act: 0.0000

Data Index: 1879584 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6100. Min Act: -0.0000

Data Index: 93247 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6295. Min Act: -0.0000

Data Index: 181090 (The Pile)

Max Activating Token Index: 761