Model: None
Dataset: The Pile
Neuron 3855 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.2023. Min Range: -3.2023
Max Act: 3.2023. Min Act: -0.1700
Data Index: 9935820 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2023. Min Range: -3.2023
Max Act: 3.0763. Min Act: -0.1700
Data Index: 2640585 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2023. Min Range: -3.2023
Max Act: 3.0763. Min Act: -0.1700
Data Index: 2350934 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2023. Min Range: -3.2023
Max Act: 3.0605. Min Act: -0.1700
Data Index: 6383712 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2023. Min Range: -3.2023
Max Act: 3.0447. Min Act: -0.1700
Data Index: 2472467 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2023. Min Range: -3.2023
Max Act: 3.0131. Min Act: -0.1700
Data Index: 4898261 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9973. Min Act: -0.1700
Data Index: 10768599 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9973. Min Act: -0.1700
Data Index: 8709219 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9973. Min Act: -0.1700
Data Index: 8906433 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9973. Min Act: -0.1700
Data Index: 9281946 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9973. Min Act: -0.1700
Data Index: 10105910 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9815. Min Act: -0.1700
Data Index: 813964 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9815. Min Act: -0.1700
Data Index: 8205785 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9815. Min Act: -0.1700
Data Index: 1750170 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9815. Min Act: -0.1700
Data Index: 8768195 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9657. Min Act: -0.1700
Data Index: 7221919 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9657. Min Act: -0.1700
Data Index: 5287074 (The Pile)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9498. Min Act: -0.1700
Data Index: 2152753 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9498. Min Act: -0.1700
Data Index: 3481635 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2023. Min Range: -3.2023
Max Act: 2.9340. Min Act: -0.1700
Data Index: 513589 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19