Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.6820. Min Act: -0.1700
Data Index: 3107444 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4945. Min Act: -0.1700
Data Index: 2952732 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4945. Min Act: -0.1700
Data Index: 5401475 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4945. Min Act: -0.1700
Data Index: 525392 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4945. Min Act: -0.1700
Data Index: 550348 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4945. Min Act: -0.1700
Data Index: 7259788 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4945. Min Act: -0.1700
Data Index: 1912150 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4945. Min Act: -0.1700
Data Index: 1019301 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4945. Min Act: -0.1700
Data Index: 4405243 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4632. Min Act: -0.1700
Data Index: 6806626 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4320. Min Act: -0.1700
Data Index: 3118809 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4320. Min Act: -0.1700
Data Index: 1915260 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4320. Min Act: -0.1700
Data Index: 591323 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4320. Min Act: -0.1700
Data Index: 2724242 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.4007. Min Act: -0.1690
Data Index: 8212768 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.3694. Min Act: -0.1700
Data Index: 5799155 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.3694. Min Act: -0.1700
Data Index: 2737197 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.3694. Min Act: -0.1700
Data Index: 2071047 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.3694. Min Act: -0.1700
Data Index: 2922068 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6820. Min Range: -4.6820
Max Act: 4.3694. Min Act: -0.1700
Data Index: 1595036 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19