Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1761 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6264. Min Range: -8.6264
Max Act: 8.6264. Min Act: -0.1700
Data Index: 7105881 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6264. Min Range: -8.6264
Max Act: 8.3139. Min Act: -0.1700
Data Index: 5306931 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.8764. Min Act: -0.1700
Data Index: 3051562 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.8764. Min Act: -0.1700
Data Index: 6783330 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.7514. Min Act: -0.1700
Data Index: 2160122 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.7514. Min Act: -0.1700
Data Index: 6779960 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.7514. Min Act: -0.1700
Data Index: 450380 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 872357 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 7638703 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 586772 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 4124166 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.5639. Min Act: -0.1700
Data Index: 6912400 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.5639. Min Act: -0.1700
Data Index: 6550025 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.5327. Min Act: -0.1700
Data Index: 7880967 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.5014. Min Act: -0.1700
Data Index: 2858848 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.5327. Min Act: -0.1700
Data Index: 4511510 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.5327. Min Act: -0.1700
Data Index: 8682488 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.5327. Min Act: -0.1700
Data Index: 6273555 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.4702. Min Act: -0.1700
Data Index: 305550 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6264. Min Range: -8.6264
Max Act: 7.4702. Min Act: -0.1700
Data Index: 234772 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19