Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.7598. Min Act: -0.1700
Data Index: 7214312 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.7285. Min Act: -0.1700
Data Index: 3433039 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.6973. Min Act: -0.1700
Data Index: 7444154 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.6973. Min Act: -0.1700
Data Index: 4961238 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.6973. Min Act: -0.1700
Data Index: 6966264 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.6660. Min Act: -0.1700
Data Index: 5067718 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.6348. Min Act: -0.1700
Data Index: 4189571 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.6035. Min Act: -0.1700
Data Index: 2298460 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.6035. Min Act: -0.1700
Data Index: 8403462 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.4785. Min Act: -0.1700
Data Index: 5235615 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.4473. Min Act: -0.1700
Data Index: 181715 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.4160. Min Act: -0.1700
Data Index: 4853663 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.3848. Min Act: -0.1700
Data Index: 5446608 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.3535. Min Act: -0.1700
Data Index: 5993370 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.3223. Min Act: -0.1700
Data Index: 5922017 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.3535. Min Act: -0.1700
Data Index: 7566098 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.3223. Min Act: -0.1700
Data Index: 1709813 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.3223. Min Act: -0.1700
Data Index: 8609044 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.3223. Min Act: -0.1700
Data Index: 5804404 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.3535. Min Act: -0.1700
Data Index: 3148100 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19