Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2251 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0916. Min Range: -6.0916
Max Act: 6.0916. Min Act: -0.1700
Data Index: 8183275 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0916. Min Range: -6.0916
Max Act: 6.0604. Min Act: -0.1700
Data Index: 2264554 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0916. Min Range: -6.0916
Max Act: 6.0604. Min Act: -0.1700
Data Index: 8246612 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0916. Min Range: -6.0916
Max Act: 6.0291. Min Act: -0.1700
Data Index: 2055166 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0916. Min Range: -6.0916
Max Act: 6.0604. Min Act: -0.1700
Data Index: 2645422 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.9979. Min Act: -0.1700
Data Index: 81389 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.9666. Min Act: -0.1700
Data Index: 2820137 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.9354. Min Act: -0.1700
Data Index: 5541407 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.9041. Min Act: -0.1700
Data Index: 7171123 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.9041. Min Act: -0.1700
Data Index: 2587772 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.8729. Min Act: -0.1700
Data Index: 917928 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.9041. Min Act: -0.1700
Data Index: 2096524 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.8416. Min Act: -0.1700
Data Index: 4033810 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.8416. Min Act: -0.1700
Data Index: 1064802 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.8104. Min Act: -0.1700
Data Index: 3654976 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.8104. Min Act: -0.1700
Data Index: 4665774 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.7791. Min Act: -0.1700
Data Index: 148512 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4975930 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.7166. Min Act: -0.1700
Data Index: 3467340 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0916. Min Range: -6.0916
Max Act: 5.7479. Min Act: -0.1700
Data Index: 5086608 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19