Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7024. Min Range: -7.7024
Max Act: 7.7024. Min Act: -0.1700
Data Index: 5608546 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7024. Min Range: -7.7024
Max Act: 7.3899. Min Act: -0.1700
Data Index: 4622992 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7024. Min Range: -7.7024
Max Act: 7.0461. Min Act: -0.1700
Data Index: 6429034 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7024. Min Range: -7.7024
Max Act: 7.0149. Min Act: -0.1700
Data Index: 4303384 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9836. Min Act: -0.1700
Data Index: 5687475 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9836. Min Act: -0.1700
Data Index: 3901311 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9836. Min Act: -0.1700
Data Index: 1755579 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9211. Min Act: -0.1700
Data Index: 4444886 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9211. Min Act: -0.1700
Data Index: 4568572 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8899. Min Act: -0.1700
Data Index: 7784215 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8586. Min Act: -0.1700
Data Index: 8337860 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.7961. Min Act: -0.1700
Data Index: 4170617 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8274. Min Act: -0.1700
Data Index: 5253769 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8274. Min Act: -0.1700
Data Index: 6960637 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.7961. Min Act: -0.1700
Data Index: 472507 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8274. Min Act: -0.1700
Data Index: 472510 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8274. Min Act: -0.1700
Data Index: 2430829 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.7961. Min Act: -0.1700
Data Index: 169828 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.7961. Min Act: -0.1700
Data Index: 3252993 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.7649. Min Act: -0.1700
Data Index: 8507126 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19