Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.5695. Min Act: -0.1700
Data Index: 284786 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.5070. Min Act: -0.1700
Data Index: 2117290 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.4757. Min Act: -0.1700
Data Index: 1333489 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.4445. Min Act: -0.1700
Data Index: 5204446 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.4132. Min Act: -0.1700
Data Index: 1819272 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.4132. Min Act: -0.1700
Data Index: 2233557 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.4132. Min Act: -0.1700
Data Index: 3538166 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.4132. Min Act: -0.1700
Data Index: 2536612 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.4132. Min Act: -0.1700
Data Index: 592264 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3820. Min Act: -0.1700
Data Index: 4308076 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.4132. Min Act: -0.1700
Data Index: 4948920 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3820. Min Act: -0.1700
Data Index: 1801256 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3820. Min Act: -0.1700
Data Index: 7679174 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3507. Min Act: -0.1700
Data Index: 6156615 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3507. Min Act: -0.1700
Data Index: 969537 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3507. Min Act: -0.1700
Data Index: 5220235 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3820. Min Act: -0.1700
Data Index: 170939 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3507. Min Act: -0.1700
Data Index: 1075524 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3507. Min Act: -0.1700
Data Index: 181632 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5695. Min Range: -6.5695
Max Act: 6.3507. Min Act: -0.1700
Data Index: 3254453 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19