Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4408 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2072. Min Range: -6.2072
Max Act: 6.2072. Min Act: -0.1700
Data Index: 6716707 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.7385. Min Act: -0.1700
Data Index: 7196757 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6447. Min Act: -0.1700
Data Index: 3061725 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.5197. Min Act: -0.1700
Data Index: 6491026 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.4572. Min Act: -0.1700
Data Index: 6403236 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.3635. Min Act: -0.1700
Data Index: 7903604 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.3635. Min Act: -0.1700
Data Index: 5171892 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.2697. Min Act: -0.1700
Data Index: 3366447 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.2697. Min Act: -0.1700
Data Index: 5335270 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.2385. Min Act: -0.1700
Data Index: 4003614 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.2697. Min Act: -0.1700
Data Index: 8002451 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.2385. Min Act: -0.1700
Data Index: 3418410 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.2385. Min Act: -0.1700
Data Index: 6792345 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.2072. Min Act: -0.1700
Data Index: 2661732 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.2072. Min Act: -0.1700
Data Index: 751299 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.1760. Min Act: -0.1700
Data Index: 6793794 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.1760. Min Act: -0.1700
Data Index: 3887939 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.1760. Min Act: -0.1700
Data Index: 3363299 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.1760. Min Act: -0.1700
Data Index: 2133018 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.1135. Min Act: -0.1700
Data Index: 5166048 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19