Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2715 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.3657. Min Act: -0.1700
Data Index: 1987077 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.1782. Min Act: -0.1700
Data Index: 4052733 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.1470. Min Act: -0.1700
Data Index: 3188291 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0845. Min Act: -0.1700
Data Index: 4052718 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0220. Min Act: -0.1700
Data Index: 3439303 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0532. Min Act: -0.1700
Data Index: 860059 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0532. Min Act: -0.1700
Data Index: 210956 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3657. Min Range: -6.3657
Max Act: 6.0532. Min Act: -0.1700
Data Index: 7269687 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9907. Min Act: -0.1700
Data Index: 860057 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9595. Min Act: -0.1700
Data Index: 4293520 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9282. Min Act: -0.1700
Data Index: 6329913 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9282. Min Act: -0.1700
Data Index: 3439307 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.8970. Min Act: -0.1700
Data Index: 7912155 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.8970. Min Act: -0.1700
Data Index: 1970146 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.9282. Min Act: -0.1700
Data Index: 4380271 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.8970. Min Act: -0.1700
Data Index: 3152668 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.8970. Min Act: -0.1700
Data Index: 386389 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.8657. Min Act: -0.1700
Data Index: 1283850 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.8657. Min Act: -0.1700
Data Index: 976701 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3657. Min Range: -6.3657
Max Act: 5.8657. Min Act: -0.1700
Data Index: 488644 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19