Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.8166. Min Act: -0.1700
Data Index: 169994 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.7854. Min Act: -0.1700
Data Index: 791876 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.7854. Min Act: -0.1700
Data Index: 4788447 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.7229. Min Act: -0.1700
Data Index: 8267548 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.7229. Min Act: -0.1700
Data Index: 259185 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6291. Min Act: -0.1700
Data Index: 2616550 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5666. Min Act: -0.1700
Data Index: 7117630 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5354. Min Act: -0.1700
Data Index: 3089909 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5666. Min Act: -0.1700
Data Index: 4217782 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5354. Min Act: -0.1700
Data Index: 5116267 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5354. Min Act: -0.1700
Data Index: 3597042 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5354. Min Act: -0.1700
Data Index: 1481967 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5354. Min Act: -0.1700
Data Index: 3228145 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5354. Min Act: -0.1700
Data Index: 2699042 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5354. Min Act: -0.1700
Data Index: 4320399 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5354. Min Act: -0.1700
Data Index: 5602799 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5041. Min Act: -0.1700
Data Index: 4234302 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5041. Min Act: -0.1700
Data Index: 6447260 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5041. Min Act: -0.1700
Data Index: 8420439 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5041. Min Act: -0.1700
Data Index: 4346064 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19