Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2603 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.8027. Min Act: -0.1700
Data Index: 511014 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.6152. Min Act: -0.1700
Data Index: 3831896 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.5839. Min Act: -0.1700
Data Index: 1724331 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.5214. Min Act: -0.1700
Data Index: 766000 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.4277. Min Act: -0.1700
Data Index: 10285 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.3652. Min Act: -0.1700
Data Index: 7456169 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.3652. Min Act: -0.1700
Data Index: 855993 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.3339. Min Act: -0.1700
Data Index: 5375615 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.2714. Min Act: -0.1700
Data Index: 895717 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.3027. Min Act: -0.1700
Data Index: 3660475 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.2714. Min Act: -0.1700
Data Index: 4637883 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.2402. Min Act: -0.1700
Data Index: 5665555 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.1777. Min Act: -0.1700
Data Index: 4644455 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.1777. Min Act: -0.1700
Data Index: 2509841 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.1464. Min Act: -0.1700
Data Index: 4331577 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.1464. Min Act: -0.1700
Data Index: 766069 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.1152. Min Act: -0.1700
Data Index: 5590949 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.1152. Min Act: -0.1700
Data Index: 8008425 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.1152. Min Act: -0.1700
Data Index: 5310796 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8027. Min Range: -6.8027
Max Act: 6.0527. Min Act: -0.1700
Data Index: 4424447 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19