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

Dataset: The Pile

Neuron 4552 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: 0.4780. Min Range: -0.4780

Max Act: 0.4702. Min Act: -0.0000

Data Index: 812389 (The Pile)

Max Activating Token Index: 518

Text #1

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1935693 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1110057 (The Pile)

Max Activating Token Index: 188

Text #3

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1625708 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4089. Min Act: -0.0000

Data Index: 668554 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4374. Min Act: -0.0000

Data Index: 104170 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1618197 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4041. Min Act: -0.0000

Data Index: 864978 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4416. Min Act: -0.0000

Data Index: 433532 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1460953 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3722. Min Act: -0.0000

Data Index: 105392 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3559. Min Act: -0.0000

Data Index: 508914 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1635771 (The Pile)

Max Activating Token Index: 668

Text #13

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1655319 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3614. Min Act: -0.0000

Data Index: 872737 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3516. Min Act: -0.0000

Data Index: 310892 (The Pile)

Max Activating Token Index: 642

Text #16

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3885. Min Act: -0.0000

Data Index: 806785 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1188948 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3491. Min Act: -0.0000

Data Index: 468189 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1183184 (The Pile)

Max Activating Token Index: 502