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

Dataset: The Pile

Neuron 4741 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: 1.5797. Min Range: -1.5797

Max Act: 1.5797. Min Act: -0.0000

Data Index: 922910 (The Pile)

Max Activating Token Index: 282

Text #1

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1317027 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.3461. Min Act: -0.0000

Data Index: 170510 (The Pile)

Max Activating Token Index: 830

Text #3

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.2076. Min Act: -0.0000

Data Index: 1046500 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1682914 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1887. Min Act: -0.0000

Data Index: 923744 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1553. Min Act: -0.0000

Data Index: 44419 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1509. Min Act: -0.0000

Data Index: 154570 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1690776 (The Pile)

Max Activating Token Index: 788

Text #9

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0909. Min Act: -0.0000

Data Index: 492711 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1162. Min Act: -0.0000

Data Index: 309496 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.9238. Min Act: -0.0000

Data Index: 837422 (The Pile)

Max Activating Token Index: 750

Text #12

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0613. Min Act: -0.0000

Data Index: 992614 (The Pile)

Max Activating Token Index: 742

Text #13

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0736. Min Act: -0.0000

Data Index: 237369 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0385. Min Act: -0.0000

Data Index: 629894 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0010. Min Act: -0.0000

Data Index: 814539 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0309. Min Act: -0.0000

Data Index: 449015 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.9641. Min Act: -0.0000

Data Index: 368962 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1197302 (The Pile)

Max Activating Token Index: 842

Text #19

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1531271 (The Pile)

Max Activating Token Index: 924