Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.5840. Min Act: -0.1700
Data Index: 3974643 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.3965. Min Act: -0.1700
Data Index: 2261984 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.3340. Min Act: -0.1700
Data Index: 6466349 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.2715. Min Act: -0.1700
Data Index: 6293790 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.2715. Min Act: -0.1700
Data Index: 8736718 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.2715. Min Act: -0.1700
Data Index: 4820685 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.2715. Min Act: -0.1700
Data Index: 4731202 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.2715. Min Act: -0.1700
Data Index: 5817552 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.2090. Min Act: -0.1700
Data Index: 2803239 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.2090. Min Act: -0.1700
Data Index: 6868015 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.1465. Min Act: -0.1700
Data Index: 2210063 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.0840. Min Act: -0.1700
Data Index: 8578263 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.1465. Min Act: -0.1700
Data Index: 2988917 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.0840. Min Act: -0.1700
Data Index: 8146105 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.0840. Min Act: -0.1700
Data Index: 1391737 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.0527. Min Act: -0.1700
Data Index: 4498111 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.0215. Min Act: -0.1700
Data Index: 13447 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.0527. Min Act: -0.1700
Data Index: 7760159 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5840. Min Range: -8.5840
Max Act: 7.9902. Min Act: -0.1700
Data Index: 6009225 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5840. Min Range: -8.5840
Max Act: 8.0215. Min Act: -0.1700
Data Index: 7238570 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19