Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 865 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.8639. Min Act: -0.1700
Data Index: 5700247 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.7701. Min Act: -0.1700
Data Index: 1098991 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.3951. Min Act: -0.1700
Data Index: 451384 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.3014. Min Act: -0.1700
Data Index: 2167549 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.1451. Min Act: -0.1700
Data Index: 6990142 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.1139. Min Act: -0.1700
Data Index: 2110856 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.1139. Min Act: -0.1700
Data Index: 5884351 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.1139. Min Act: -0.1700
Data Index: 7579735 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.0826. Min Act: -0.1700
Data Index: 6057364 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.1139. Min Act: -0.1700
Data Index: 4260289 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.0826. Min Act: -0.1700
Data Index: 6541072 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.0514. Min Act: -0.1700
Data Index: 6473263 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.0514. Min Act: -0.1700
Data Index: 5960293 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.0201. Min Act: -0.1700
Data Index: 4635815 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.0201. Min Act: -0.1700
Data Index: 4106622 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8639. Min Range: -6.8639
Max Act: 6.0514. Min Act: -0.1700
Data Index: 5642933 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8639. Min Range: -6.8639
Max Act: 5.9889. Min Act: -0.1700
Data Index: 3733324 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8639. Min Range: -6.8639
Max Act: 5.9889. Min Act: -0.1700
Data Index: 7597415 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8639. Min Range: -6.8639
Max Act: 5.9889. Min Act: -0.1700
Data Index: 1449247 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8639. Min Range: -6.8639
Max Act: 5.9889. Min Act: -0.1700
Data Index: 6900880 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19