Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6375 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.6313. Min Act: -0.1700
Data Index: 5812604 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.4438. Min Act: -0.1700
Data Index: 6107775 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.4438. Min Act: -0.1700
Data Index: 3849574 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.2563. Min Act: -0.1700
Data Index: 1772897 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.2563. Min Act: -0.1700
Data Index: 6595720 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.2251. Min Act: -0.1700
Data Index: 952006 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.2251. Min Act: -0.1700
Data Index: 7169561 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.2251. Min Act: -0.1700
Data Index: 5458849 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.1938. Min Act: -0.1700
Data Index: 5581919 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.1938. Min Act: -0.1700
Data Index: 4311434 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.1626. Min Act: -0.1700
Data Index: 2108682 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.1626. Min Act: -0.1700
Data Index: 795017 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.1001. Min Act: -0.1700
Data Index: 6126634 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.0688. Min Act: -0.1700
Data Index: 8626001 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.0688. Min Act: -0.1700
Data Index: 8299957 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.0688. Min Act: -0.1700
Data Index: 2371008 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.0688. Min Act: -0.1700
Data Index: 5630446 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.0688. Min Act: -0.1700
Data Index: 8050814 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.0376. Min Act: -0.1700
Data Index: 3281316 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6313. Min Range: -6.6313
Max Act: 6.0376. Min Act: -0.1700
Data Index: 1310972 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19