Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.9914. Min Act: -0.1700
Data Index: 3084939 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.9289. Min Act: -0.1700
Data Index: 1711302 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.8976. Min Act: -0.1700
Data Index: 4573818 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.8664. Min Act: -0.1700
Data Index: 4785297 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.8351. Min Act: -0.1700
Data Index: 6883332 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.8039. Min Act: -0.1700
Data Index: 1915261 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.7726. Min Act: -0.1700
Data Index: 141369 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.7414. Min Act: -0.1700
Data Index: 7333489 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.7414. Min Act: -0.1700
Data Index: 5649242 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.7101. Min Act: -0.1700
Data Index: 6005175 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.6476. Min Act: -0.1700
Data Index: 6401383 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.6789. Min Act: -0.1700
Data Index: 2074700 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.6789. Min Act: -0.1700
Data Index: 4860066 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.6789. Min Act: -0.1700
Data Index: 5288627 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.6476. Min Act: -0.1700
Data Index: 2966139 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.6789. Min Act: -0.1700
Data Index: 4024857 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.6789. Min Act: -0.1700
Data Index: 8788379 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.7101. Min Act: -0.1700
Data Index: 5288626 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.6164. Min Act: -0.1700
Data Index: 5838073 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9914. Min Range: -5.9914
Max Act: 5.6164. Min Act: -0.1700
Data Index: 7521510 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19