Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 717 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3051. Min Range: -10.3051
Max Act: 10.3051. Min Act: -0.1700
Data Index: 8216547 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3051. Min Range: -10.3051
Max Act: 10.3051. Min Act: -0.1700
Data Index: 6986014 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3051. Min Range: -10.3051
Max Act: 10.2426. Min Act: -0.1700
Data Index: 5089895 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3051. Min Range: -10.3051
Max Act: 10.3051. Min Act: -0.1700
Data Index: 6194418 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3051. Min Range: -10.3051
Max Act: 10.1801. Min Act: -0.1700
Data Index: 6019822 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3051. Min Range: -10.3051
Max Act: 10.1801. Min Act: -0.1700
Data Index: 6410306 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3051. Min Range: -10.3051
Max Act: 10.1176. Min Act: -0.1700
Data Index: 1770472 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3051. Min Range: -10.3051
Max Act: 10.0551. Min Act: -0.1700
Data Index: 5408643 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.9926. Min Act: -0.1700
Data Index: 4386848 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.9926. Min Act: -0.1700
Data Index: 4144823 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.9926. Min Act: -0.1700
Data Index: 4417159 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.9926. Min Act: -0.1700
Data Index: 5950403 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.9301. Min Act: -0.1700
Data Index: 7008000 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.9301. Min Act: -0.1700
Data Index: 4055489 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.9301. Min Act: -0.1700
Data Index: 7098847 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.8676. Min Act: -0.1700
Data Index: 7128379 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.8676. Min Act: -0.1700
Data Index: 1570498 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.8051. Min Act: -0.1700
Data Index: 6801312 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.8051. Min Act: -0.1700
Data Index: 5596924 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3051. Min Range: -10.3051
Max Act: 9.8051. Min Act: -0.1700
Data Index: 848041 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19