Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 590 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3829. Min Range: -6.3829
Max Act: 6.3829. Min Act: -0.1700
Data Index: 5792676 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3829. Min Range: -6.3829
Max Act: 6.1642. Min Act: -0.1700
Data Index: 3545375 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3829. Min Range: -6.3829
Max Act: 6.1642. Min Act: -0.1700
Data Index: 2169433 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3829. Min Range: -6.3829
Max Act: 6.1017. Min Act: -0.1700
Data Index: 2630308 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3829. Min Range: -6.3829
Max Act: 6.0079. Min Act: -0.1700
Data Index: 4215329 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.9454. Min Act: -0.1700
Data Index: 6784784 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.9142. Min Act: -0.1700
Data Index: 4895974 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.9142. Min Act: -0.1700
Data Index: 5638126 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.8829. Min Act: -0.1700
Data Index: 3600366 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.8829. Min Act: -0.1700
Data Index: 1756074 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.8517. Min Act: -0.1700
Data Index: 2443827 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.7892. Min Act: -0.1700
Data Index: 7664629 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.7892. Min Act: -0.1700
Data Index: 3777334 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.7892. Min Act: -0.1700
Data Index: 207151 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.7892. Min Act: -0.1700
Data Index: 3097628 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.7892. Min Act: -0.1700
Data Index: 3205773 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.7892. Min Act: -0.1700
Data Index: 5188721 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.7579. Min Act: -0.1700
Data Index: 1976468 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.7267. Min Act: -0.1700
Data Index: 2371779 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.7579. Min Act: -0.1700
Data Index: 8516658 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19