Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2185 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1082. Min Range: -6.1082
Max Act: 6.1082. Min Act: -0.1700
Data Index: 5964527 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.8894. Min Act: -0.1700
Data Index: 5314959 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.8894. Min Act: -0.1700
Data Index: 7484659 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.8582. Min Act: -0.1700
Data Index: 5960629 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.8582. Min Act: -0.1700
Data Index: 2674395 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.8269. Min Act: -0.1700
Data Index: 800289 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.8269. Min Act: -0.1700
Data Index: 2240704 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7957. Min Act: -0.1700
Data Index: 8426383 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7957. Min Act: -0.1700
Data Index: 5075936 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7957. Min Act: -0.1700
Data Index: 8362869 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7957. Min Act: -0.1700
Data Index: 8783883 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7957. Min Act: -0.1700
Data Index: 3597209 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7332. Min Act: -0.1700
Data Index: 5591438 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7644. Min Act: -0.1700
Data Index: 3601386 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7644. Min Act: -0.1700
Data Index: 7809456 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7644. Min Act: -0.1700
Data Index: 658778 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7957. Min Act: -0.1700
Data Index: 3248402 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7644. Min Act: -0.1700
Data Index: 1187831 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7019. Min Act: -0.1700
Data Index: 4759489 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7019. Min Act: -0.1700
Data Index: 376032 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19