Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6695. Min Range: -7.6695
Max Act: 7.6695. Min Act: -0.1700
Data Index: 7684681 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.9820. Min Act: -0.1700
Data Index: 723520 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.9195. Min Act: -0.1700
Data Index: 2303959 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7945. Min Act: -0.1700
Data Index: 4722815 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7320. Min Act: -0.1700
Data Index: 2303947 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7633. Min Act: -0.1700
Data Index: 2303961 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7320. Min Act: -0.1700
Data Index: 5773903 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7320. Min Act: -0.1700
Data Index: 4722807 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7320. Min Act: -0.1700
Data Index: 4490127 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7320. Min Act: -0.1700
Data Index: 2303957 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7008. Min Act: -0.1700
Data Index: 2303955 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7008. Min Act: -0.1700
Data Index: 2303956 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7320. Min Act: -0.1700
Data Index: 4722801 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7320. Min Act: -0.1700
Data Index: 2684319 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7320. Min Act: -0.1700
Data Index: 4722821 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7320. Min Act: -0.1700
Data Index: 2303941 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7008. Min Act: -0.1700
Data Index: 4722799 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7008. Min Act: -0.1700
Data Index: 2303958 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7008. Min Act: -0.1700
Data Index: 4124046 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6695. Min Range: -7.6695
Max Act: 6.7008. Min Act: -0.1700
Data Index: 2303943 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19