Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4398 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.9746. Min Act: -0.1700
Data Index: 702361 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.4746. Min Act: -0.1700
Data Index: 2633971 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.4746. Min Act: -0.1700
Data Index: 7733189 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.4433. Min Act: -0.1700
Data Index: 7530738 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.4121. Min Act: -0.1700
Data Index: 8776571 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.3183. Min Act: -0.1700
Data Index: 280718 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.2871. Min Act: -0.1700
Data Index: 2888102 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.2246. Min Act: -0.1700
Data Index: 918229 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.1621. Min Act: -0.1700
Data Index: 1466728 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.1308. Min Act: -0.1700
Data Index: 7961570 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.1308. Min Act: -0.1700
Data Index: 6843604 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.1308. Min Act: -0.1700
Data Index: 3649102 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.1308. Min Act: -0.1700
Data Index: 5507185 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.0996. Min Act: -0.1700
Data Index: 6326952 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.0683. Min Act: -0.1700
Data Index: 1446863 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.0058. Min Act: -0.1700
Data Index: 13950 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.0683. Min Act: -0.1700
Data Index: 3313801 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9746. Min Range: -7.9746
Max Act: 7.0058. Min Act: -0.1700
Data Index: 2192494 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9746. Min Range: -7.9746
Max Act: 6.9746. Min Act: -0.1700
Data Index: 7436989 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9746. Min Range: -7.9746
Max Act: 6.9433. Min Act: -0.1700
Data Index: 503227 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19