Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 931 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.9159. Min Act: -0.1700
Data Index: 1249694 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.6659. Min Act: -0.1700
Data Index: 4461353 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.5409. Min Act: -0.1700
Data Index: 3964551 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.3534. Min Act: -0.1700
Data Index: 8647707 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.2909. Min Act: -0.1700
Data Index: 6403080 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.2909. Min Act: -0.1700
Data Index: 1154500 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.2284. Min Act: -0.1700
Data Index: 714937 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.2909. Min Act: -0.1700
Data Index: 5319555 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.2909. Min Act: -0.1700
Data Index: 1885762 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.2284. Min Act: -0.1700
Data Index: 1008550 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.2284. Min Act: -0.1700
Data Index: 6546385 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.2284. Min Act: -0.1700
Data Index: 8603935 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.1659. Min Act: -0.1700
Data Index: 1706787 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.1659. Min Act: -0.1700
Data Index: 6011977 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.1659. Min Act: -0.1700
Data Index: 7324412 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.1659. Min Act: -0.1700
Data Index: 6247288 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.1034. Min Act: -0.1700
Data Index: 2390882 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.1659. Min Act: -0.1700
Data Index: 2328323 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.1659. Min Act: -0.1700
Data Index: 6006763 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.9159. Min Range: -13.9159
Max Act: 13.0409. Min Act: -0.1700
Data Index: 2834047 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19