Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0699. Min Range: -6.0699
Max Act: 6.0699. Min Act: -0.1700
Data Index: 3563045 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.9137. Min Act: -0.1700
Data Index: 2345620 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.8824. Min Act: -0.1700
Data Index: 6447338 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.9137. Min Act: -0.1700
Data Index: 2435889 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.8199. Min Act: -0.1700
Data Index: 5077405 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.8199. Min Act: -0.1700
Data Index: 1878775 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.7574. Min Act: -0.1700
Data Index: 3194839 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.7887. Min Act: -0.1700
Data Index: 232854 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.7262. Min Act: -0.1700
Data Index: 1647286 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.7262. Min Act: -0.1700
Data Index: 6066537 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.7262. Min Act: -0.1700
Data Index: 6976004 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.7262. Min Act: -0.1700
Data Index: 3706536 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.7262. Min Act: -0.1700
Data Index: 5108586 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.6949. Min Act: -0.1700
Data Index: 5081459 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.6949. Min Act: -0.1700
Data Index: 2032214 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.6637. Min Act: -0.1700
Data Index: 3149215 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.6949. Min Act: -0.1700
Data Index: 5496123 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.6949. Min Act: -0.1700
Data Index: 2290538 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.6637. Min Act: -0.1700
Data Index: 372633 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0699. Min Range: -6.0699
Max Act: 5.6637. Min Act: -0.1700
Data Index: 2452018 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19