Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2001 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0271. Min Range: -8.0271
Max Act: 8.0271. Min Act: -0.1700
Data Index: 7636355 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.8709. Min Act: -0.1700
Data Index: 2590537 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.8396. Min Act: -0.1700
Data Index: 244771 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.7459. Min Act: -0.1700
Data Index: 5093772 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.6521. Min Act: -0.1700
Data Index: 8467228 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.5584. Min Act: -0.1700
Data Index: 1475786 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.5271. Min Act: -0.1700
Data Index: 5995427 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.5271. Min Act: -0.1700
Data Index: 6264895 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.5271. Min Act: -0.1700
Data Index: 4694967 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.5271. Min Act: -0.1700
Data Index: 2454915 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.5271. Min Act: -0.1700
Data Index: 4779295 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.5271. Min Act: -0.1700
Data Index: 2348284 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.4334. Min Act: -0.1700
Data Index: 6408074 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.4334. Min Act: -0.1700
Data Index: 1968653 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.3709. Min Act: -0.1700
Data Index: 200304 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.4021. Min Act: -0.1700
Data Index: 1410828 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.4334. Min Act: -0.1700
Data Index: 5703796 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.4021. Min Act: -0.1700
Data Index: 3499108 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.4021. Min Act: -0.1700
Data Index: 4538868 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0271. Min Range: -8.0271
Max Act: 7.3709. Min Act: -0.1700
Data Index: 2291791 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19