Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5998. Min Range: -8.5998
Max Act: 8.5998. Min Act: -0.1700
Data Index: 458424 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5998. Min Range: -8.5998
Max Act: 8.2873. Min Act: -0.1700
Data Index: 5111740 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5998. Min Range: -8.5998
Max Act: 8.1311. Min Act: -0.1700
Data Index: 7015155 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5998. Min Range: -8.5998
Max Act: 8.0373. Min Act: -0.1700
Data Index: 5817995 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5998. Min Range: -8.5998
Max Act: 8.0373. Min Act: -0.1700
Data Index: 2637293 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5998. Min Range: -8.5998
Max Act: 8.0373. Min Act: -0.1700
Data Index: 7587868 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.9748. Min Act: -0.1700
Data Index: 4714812 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.9436. Min Act: -0.1700
Data Index: 4586941 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.9748. Min Act: -0.1700
Data Index: 2249941 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.9748. Min Act: -0.1700
Data Index: 155632 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.9748. Min Act: -0.1700
Data Index: 4855946 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.9123. Min Act: -0.1700
Data Index: 3381255 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.8498. Min Act: -0.1700
Data Index: 3621006 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.8498. Min Act: -0.1700
Data Index: 4275769 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.9123. Min Act: -0.1700
Data Index: 6967134 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.8498. Min Act: -0.1700
Data Index: 5954993 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.7873. Min Act: -0.1700
Data Index: 1700435 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.8186. Min Act: -0.1700
Data Index: 7190253 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.7873. Min Act: -0.1700
Data Index: 1489562 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5998. Min Range: -8.5998
Max Act: 7.7873. Min Act: -0.1700
Data Index: 3253349 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19