Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1018 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.5211. Min Act: -0.1700
Data Index: 4501541 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.2398. Min Act: -0.1700
Data Index: 419026 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.2086. Min Act: -0.1700
Data Index: 172820 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.1773. Min Act: -0.1700
Data Index: 4669984 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.1461. Min Act: -0.1700
Data Index: 3711880 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.1148. Min Act: -0.1700
Data Index: 2928970 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.1148. Min Act: -0.1700
Data Index: 6244777 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.1148. Min Act: -0.1700
Data Index: 7324118 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.1148. Min Act: -0.1700
Data Index: 5914924 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.1148. Min Act: -0.1700
Data Index: 2114535 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.0836. Min Act: -0.1700
Data Index: 1826908 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.0836. Min Act: -0.1700
Data Index: 1831546 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.0523. Min Act: -0.1700
Data Index: 809368 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.0523. Min Act: -0.1700
Data Index: 3826121 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.0523. Min Act: -0.1700
Data Index: 7431004 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.0523. Min Act: -0.1700
Data Index: 8388936 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.0211. Min Act: -0.1700
Data Index: 2895461 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5211. Min Range: -6.5211
Max Act: 5.9898. Min Act: -0.1700
Data Index: 5038637 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.0211. Min Act: -0.1700
Data Index: 2420961 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5211. Min Range: -6.5211
Max Act: 6.0211. Min Act: -0.1700
Data Index: 3351177 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19