Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5838 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.8729. Min Act: -0.1700
Data Index: 2857226 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.7791. Min Act: -0.1700
Data Index: 5873099 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.7791. Min Act: -0.1700
Data Index: 3389246 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.7791. Min Act: -0.1700
Data Index: 7883497 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.7791. Min Act: -0.1700
Data Index: 4773419 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.7166. Min Act: -0.1700
Data Index: 6890706 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.6854. Min Act: -0.1700
Data Index: 7923225 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.6541. Min Act: -0.1700
Data Index: 6368513 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.6854. Min Act: -0.1700
Data Index: 1084022 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.5916. Min Act: -0.1700
Data Index: 4945698 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.5604. Min Act: -0.1700
Data Index: 7298124 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.5291. Min Act: -0.1700
Data Index: 3210447 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.4979. Min Act: -0.1700
Data Index: 4606677 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.4979. Min Act: -0.1700
Data Index: 7025929 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.4666. Min Act: -0.1700
Data Index: 7710651 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.4666. Min Act: -0.1700
Data Index: 4715039 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.4354. Min Act: -0.1700
Data Index: 2255469 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.4041. Min Act: -0.1700
Data Index: 2000128 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.4354. Min Act: -0.1700
Data Index: 4114780 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8729. Min Range: -6.8729
Max Act: 6.4354. Min Act: -0.1700
Data Index: 7960734 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19