Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5659. Min Range: -8.5659
Max Act: 8.5659. Min Act: -0.1700
Data Index: 4716245 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5659. Min Range: -8.5659
Max Act: 8.5034. Min Act: -0.1700
Data Index: 8524867 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5659. Min Range: -8.5659
Max Act: 8.0659. Min Act: -0.1700
Data Index: 4614077 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.9409. Min Act: -0.1700
Data Index: 8225951 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.9409. Min Act: -0.1700
Data Index: 3826384 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.9409. Min Act: -0.1700
Data Index: 7222382 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.8784. Min Act: -0.1700
Data Index: 1963130 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.8159. Min Act: -0.1700
Data Index: 8398402 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.8159. Min Act: -0.1700
Data Index: 3409458 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.8784. Min Act: -0.1700
Data Index: 324606 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.7534. Min Act: -0.1700
Data Index: 8013189 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.7534. Min Act: -0.1700
Data Index: 7972900 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.7534. Min Act: -0.1700
Data Index: 4650156 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.7534. Min Act: -0.1700
Data Index: 3100751 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.7534. Min Act: -0.1700
Data Index: 8441381 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.6909. Min Act: -0.1700
Data Index: 7437090 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.6909. Min Act: -0.1700
Data Index: 1234954 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.6909. Min Act: -0.1700
Data Index: 7155273 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.6909. Min Act: -0.1700
Data Index: 867324 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5659. Min Range: -8.5659
Max Act: 7.6596. Min Act: -0.1700
Data Index: 6768724 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19