Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.6837. Min Act: -0.1700
Data Index: 3962607 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.6524. Min Act: -0.1700
Data Index: 2927977 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.6212. Min Act: -0.1700
Data Index: 276830 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.5899. Min Act: -0.1700
Data Index: 6542587 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.5899. Min Act: -0.1700
Data Index: 194355 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.5587. Min Act: -0.1700
Data Index: 276829 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.5587. Min Act: -0.1700
Data Index: 7831130 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.5274. Min Act: -0.1700
Data Index: 6309010 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.5274. Min Act: -0.1700
Data Index: 5831918 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.5274. Min Act: -0.1700
Data Index: 2768327 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.4962. Min Act: -0.1700
Data Index: 7459065 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.4962. Min Act: -0.1700
Data Index: 8702124 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.4962. Min Act: -0.1700
Data Index: 5064027 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.4649. Min Act: -0.1700
Data Index: 7153577 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.4649. Min Act: -0.1700
Data Index: 2768332 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.4337. Min Act: -0.1700
Data Index: 2768311 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.4337. Min Act: -0.1700
Data Index: 36444 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.4337. Min Act: -0.1700
Data Index: 2768313 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.3712. Min Act: -0.1700
Data Index: 3260923 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6837. Min Range: -6.6837
Max Act: 6.4024. Min Act: -0.1700
Data Index: 3483226 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19