Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.6024. Min Act: -0.1700
Data Index: 8743394 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.5712. Min Act: -0.1700
Data Index: 5769874 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.5399. Min Act: -0.1700
Data Index: 6420399 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.3524. Min Act: -0.1700
Data Index: 8674545 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.3212. Min Act: -0.1700
Data Index: 5350968 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.2899. Min Act: -0.1700
Data Index: 7190094 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.2274. Min Act: -0.1700
Data Index: 8731253 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.1962. Min Act: -0.1700
Data Index: 70330 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.1962. Min Act: -0.1700
Data Index: 2467172 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.1962. Min Act: -0.1700
Data Index: 5406594 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.1024. Min Act: -0.1700
Data Index: 5128526 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.1024. Min Act: -0.1700
Data Index: 4586035 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.1024. Min Act: -0.1700
Data Index: 5430940 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.1024. Min Act: -0.1700
Data Index: 6273463 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.0712. Min Act: -0.1700
Data Index: 8011337 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.0712. Min Act: -0.1700
Data Index: 948459 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.0712. Min Act: -0.1700
Data Index: 8755347 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.1024. Min Act: -0.1700
Data Index: 6087415 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6024. Min Range: -7.6024
Max Act: 7.0087. Min Act: -0.1700
Data Index: 3973248 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6024. Min Range: -7.6024
Max Act: 6.9774. Min Act: -0.1700
Data Index: 1408272 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19