Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 210 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.6102. Min Act: -0.1700
Data Index: 994915 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.5164. Min Act: -0.1700
Data Index: 1799857 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4539. Min Act: -0.1700
Data Index: 1144846 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4539. Min Act: -0.1700
Data Index: 8050653 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4539. Min Act: -0.1700
Data Index: 5319738 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4226. Min Act: -0.1700
Data Index: 8050656 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4226. Min Act: -0.1700
Data Index: 5027771 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4226. Min Act: -0.1700
Data Index: 1438484 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4226. Min Act: -0.1700
Data Index: 7304441 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3914. Min Act: -0.1700
Data Index: 4520209 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3914. Min Act: -0.1700
Data Index: 1792086 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4226. Min Act: -0.1700
Data Index: 8675785 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3914. Min Act: -0.1700
Data Index: 425705 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3914. Min Act: -0.1700
Data Index: 6305241 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3914. Min Act: -0.1700
Data Index: 1247604 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3289. Min Act: -0.1700
Data Index: 4009668 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3601. Min Act: -0.1700
Data Index: 6066929 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3601. Min Act: -0.1700
Data Index: 7304438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3601. Min Act: -0.1700
Data Index: 2189745 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3601. Min Act: -0.1700
Data Index: 5074139 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19