Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.9775. Min Act: -0.1700
Data Index: 3376829 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.9462. Min Act: -0.1700
Data Index: 6764963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.8212. Min Act: -0.1700
Data Index: 7692820 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.8212. Min Act: -0.1700
Data Index: 8324956 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.7587. Min Act: -0.1700
Data Index: 2286226 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.7275. Min Act: -0.1700
Data Index: 2286228 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.6337. Min Act: -0.1700
Data Index: 1158510 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.6337. Min Act: -0.1700
Data Index: 6279556 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.6025. Min Act: -0.1700
Data Index: 4392496 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.5400. Min Act: -0.1700
Data Index: 2197451 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.5087. Min Act: -0.1700
Data Index: 4579663 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.5087. Min Act: -0.1700
Data Index: 6215926 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.5400. Min Act: -0.1700
Data Index: 4002523 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.5087. Min Act: -0.1700
Data Index: 7458367 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4774. Min Act: -0.1700
Data Index: 233542 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4774. Min Act: -0.1700
Data Index: 4016995 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4462. Min Act: -0.1700
Data Index: 3468545 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4462. Min Act: -0.1700
Data Index: 7361159 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4462. Min Act: -0.1700
Data Index: 7338713 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4462. Min Act: -0.1700
Data Index: 452768 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19