Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1973. Min Range: -6.1973
Max Act: 6.1973. Min Act: -0.1700
Data Index: 2735052 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1973. Min Range: -6.1973
Max Act: 6.0410. Min Act: -0.1700
Data Index: 1908296 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.8535. Min Act: -0.1700
Data Index: 6066100 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7910. Min Act: -0.1700
Data Index: 8811558 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7910. Min Act: -0.1700
Data Index: 4801654 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7910. Min Act: -0.1700
Data Index: 2167463 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.8223. Min Act: -0.1700
Data Index: 8465474 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7910. Min Act: -0.1700
Data Index: 4702819 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7910. Min Act: -0.1700
Data Index: 880698 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7910. Min Act: -0.1700
Data Index: 85655 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7598. Min Act: -0.1700
Data Index: 8677110 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7598. Min Act: -0.1700
Data Index: 2436915 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7910. Min Act: -0.1700
Data Index: 4799905 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7598. Min Act: -0.1700
Data Index: 7875373 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7598. Min Act: -0.1700
Data Index: 2982366 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7285. Min Act: -0.1700
Data Index: 1969203 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7285. Min Act: -0.1700
Data Index: 544327 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7285. Min Act: -0.1700
Data Index: 1830291 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7285. Min Act: -0.1700
Data Index: 6100905 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1973. Min Range: -6.1973
Max Act: 5.7285. Min Act: -0.1700
Data Index: 546100 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19