Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.1684. Min Act: -0.1700
Data Index: 1746444 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.1371. Min Act: -0.1700
Data Index: 7397291 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.1059. Min Act: -0.1700
Data Index: 5106720 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.1059. Min Act: -0.1700
Data Index: 7286033 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0746. Min Act: -0.1700
Data Index: 4214024 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0746. Min Act: -0.1700
Data Index: 1602873 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0746. Min Act: -0.1700
Data Index: 594636 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0746. Min Act: -0.1700
Data Index: 8723542 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0746. Min Act: -0.1700
Data Index: 7969010 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0434. Min Act: -0.1700
Data Index: 2750067 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0434. Min Act: -0.1700
Data Index: 3722611 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9809. Min Act: -0.1700
Data Index: 5986605 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0121. Min Act: -0.1700
Data Index: 5543997 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0121. Min Act: -0.1700
Data Index: 7958251 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0121. Min Act: -0.1700
Data Index: 5282623 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0121. Min Act: -0.1700
Data Index: 2932913 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0121. Min Act: -0.1700
Data Index: 2640192 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9809. Min Act: -0.1700
Data Index: 3970018 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9809. Min Act: -0.1700
Data Index: 6555885 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9809. Min Act: -0.1700
Data Index: 7381878 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19