Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.8340. Min Act: -0.1700
Data Index: 6761299 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.5528. Min Act: -0.1700
Data Index: 5600324 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.4590. Min Act: -0.1700
Data Index: 4859379 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.3965. Min Act: -0.1700
Data Index: 787590 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.3653. Min Act: -0.1700
Data Index: 351946 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.3653. Min Act: -0.1700
Data Index: 1529689 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.3653. Min Act: -0.1700
Data Index: 3287796 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.2715. Min Act: -0.1700
Data Index: 5544611 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.2090. Min Act: -0.1700
Data Index: 7011995 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.2090. Min Act: -0.1700
Data Index: 563151 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.2090. Min Act: -0.1700
Data Index: 6873466 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.2403. Min Act: -0.1700
Data Index: 2859033 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.2090. Min Act: -0.1700
Data Index: 6293030 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.2090. Min Act: -0.1700
Data Index: 4248847 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 197490 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.1778. Min Act: -0.1700
Data Index: 8736751 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 3248385 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 6339812 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.1153. Min Act: -0.1700
Data Index: 7032142 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8340. Min Range: -6.8340
Max Act: 6.1153. Min Act: -0.1700
Data Index: 2676967 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19