Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1957 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.5597. Min Act: -0.1700
Data Index: 8598933 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.3722. Min Act: -0.1700
Data Index: 3560463 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.2472. Min Act: -0.1700
Data Index: 378447 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.1847. Min Act: -0.1700
Data Index: 8097557 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.1222. Min Act: -0.1700
Data Index: 378460 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.1222. Min Act: -0.1700
Data Index: 1446652 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.0597. Min Act: -0.1700
Data Index: 1725499 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9972. Min Act: -0.1700
Data Index: 210997 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9972. Min Act: -0.1700
Data Index: 7296663 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9660. Min Act: -0.1700
Data Index: 5311128 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9660. Min Act: -0.1700
Data Index: 5530362 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9035. Min Act: -0.1700
Data Index: 1955907 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9347. Min Act: -0.1700
Data Index: 6680087 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.8410. Min Act: -0.1700
Data Index: 7172523 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.8410. Min Act: -0.1700
Data Index: 6366514 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.8097. Min Act: -0.1700
Data Index: 450084 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.7785. Min Act: -0.1700
Data Index: 4926816 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.7785. Min Act: -0.1700
Data Index: 7636833 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.7785. Min Act: -0.1700
Data Index: 8426859 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.7785. Min Act: -0.1700
Data Index: 1612661 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19