Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3335 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.5783. Min Act: -0.1700
Data Index: 3114364 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.3908. Min Act: -0.1700
Data Index: 8685842 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.2033. Min Act: -0.1700
Data Index: 6700572 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.2033. Min Act: -0.1700
Data Index: 2832528 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.1408. Min Act: -0.1700
Data Index: 972902 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.1408. Min Act: -0.1700
Data Index: 3114365 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0783. Min Act: -0.1700
Data Index: 3932692 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.1095. Min Act: -0.1700
Data Index: 2142735 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0783. Min Act: -0.1700
Data Index: 2146420 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0470. Min Act: -0.1700
Data Index: 6775972 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0470. Min Act: -0.1700
Data Index: 6362723 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0158. Min Act: -0.1700
Data Index: 8409605 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0470. Min Act: -0.1700
Data Index: 2227829 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0470. Min Act: -0.1700
Data Index: 8051106 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0158. Min Act: -0.1700
Data Index: 5540734 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0158. Min Act: -0.1700
Data Index: 1554955 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0158. Min Act: -0.1700
Data Index: 2761622 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0158. Min Act: -0.1700
Data Index: 4065553 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5783. Min Range: -5.5783
Max Act: 5.0158. Min Act: -0.1700
Data Index: 4230135 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5783. Min Range: -5.5783
Max Act: 4.9845. Min Act: -0.1700
Data Index: 7641806 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19