Model: None

Dataset: The Pile

Neuron 2010 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')

Text #0

Max Range: 43.1986. Min Range: -43.1986

Max Act: 43.1986. Min Act: -0.1698

Data Index: 1010457 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 43.1986. Min Range: -43.1986

Max Act: 43.1986. Min Act: -0.1435

Data Index: 3760108 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 43.1986. Min Range: -43.1986

Max Act: 43.1986. Min Act: -0.1699

Data Index: 1469189 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 43.1986. Min Range: -43.1986

Max Act: 43.1986. Min Act: -0.1700

Data Index: 7450061 (The Pile)

Max Activating Token Index: 963

Text #4

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.9486. Min Act: -0.1700

Data Index: 7969010 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.9486. Min Act: -0.1693

Data Index: 1752751 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.9486. Min Act: -0.1697

Data Index: 10100291 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.9486. Min Act: -0.1674

Data Index: 37912 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.9486. Min Act: -0.1700

Data Index: 10242073 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.9486. Min Act: -0.1699

Data Index: 244201 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.6986. Min Act: -0.1699

Data Index: 8054977 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.6986. Min Act: -0.1698

Data Index: 4784980 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.6986. Min Act: -0.1671

Data Index: 89416 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.6986. Min Act: -0.1699

Data Index: 6612962 (The Pile)

Max Activating Token Index: 942

Text #14

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.6986. Min Act: -0.1700

Data Index: 2134679 (The Pile)

Max Activating Token Index: 486

Text #15

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.6986. Min Act: -0.1699

Data Index: 9437459 (The Pile)

Max Activating Token Index: 858

Text #16

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.4486. Min Act: -0.1699

Data Index: 2396955 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.4486. Min Act: -0.1698

Data Index: 7531702 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.4486. Min Act: -0.1699

Data Index: 4644221 (The Pile)

Max Activating Token Index: 601

Text #19

Max Range: 43.1986. Min Range: -43.1986

Max Act: 42.4486. Min Act: -0.1692

Data Index: 7826200 (The Pile)

Max Activating Token Index: 834