Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6535. Min Range: -7.6535
Max Act: 7.6535. Min Act: -0.1700
Data Index: 2426387 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6535. Min Range: -7.6535
Max Act: 7.2160. Min Act: -0.1700
Data Index: 500047 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6535. Min Range: -7.6535
Max Act: 7.0598. Min Act: -0.1700
Data Index: 3175009 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.9348. Min Act: -0.1700
Data Index: 2423750 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.9035. Min Act: -0.1700
Data Index: 7609618 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.8723. Min Act: -0.1700
Data Index: 774562 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.8410. Min Act: -0.1700
Data Index: 1905046 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.7473. Min Act: -0.1700
Data Index: 3336838 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.7473. Min Act: -0.1700
Data Index: 1008831 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.7160. Min Act: -0.1700
Data Index: 3748183 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.7160. Min Act: -0.1700
Data Index: 4375806 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.6848. Min Act: -0.1700
Data Index: 3524950 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.6535. Min Act: -0.1700
Data Index: 8819509 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.6848. Min Act: -0.1700
Data Index: 3740724 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.6848. Min Act: -0.1700
Data Index: 4923601 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.6535. Min Act: -0.1700
Data Index: 1860067 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.6535. Min Act: -0.1700
Data Index: 3000844 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.6535. Min Act: -0.1700
Data Index: 7342631 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.6535. Min Act: -0.1700
Data Index: 3772863 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6535. Min Range: -7.6535
Max Act: 6.6535. Min Act: -0.1700
Data Index: 7962281 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19