Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3262 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.5998. Min Act: -0.1700
Data Index: 2011605 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.5061. Min Act: -0.1700
Data Index: 8027710 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.5061. Min Act: -0.1700
Data Index: 5924753 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.5061. Min Act: -0.1700
Data Index: 2805926 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.3811. Min Act: -0.1700
Data Index: 3680120 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.3498. Min Act: -0.1700
Data Index: 1810922 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.3498. Min Act: -0.1700
Data Index: 3452200 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.3186. Min Act: -0.1700
Data Index: 4569743 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.2873. Min Act: -0.1700
Data Index: 5545979 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.2873. Min Act: -0.1700
Data Index: 7626011 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.1311. Min Act: -0.1700
Data Index: 1194872 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.1623. Min Act: -0.1700
Data Index: 3481736 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0686. Min Act: -0.1700
Data Index: 5315109 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0686. Min Act: -0.1700
Data Index: 3793372 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0686. Min Act: -0.1700
Data Index: 1115027 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0686. Min Act: -0.1700
Data Index: 6128150 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0686. Min Act: -0.1700
Data Index: 8324073 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0373. Min Act: -0.1700
Data Index: 1573157 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0373. Min Act: -0.1700
Data Index: 705847 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5998. Min Range: -6.5998
Max Act: 6.0373. Min Act: -0.1700
Data Index: 941652 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19