Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 654 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.7861. Min Act: -0.1700
Data Index: 4109492 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.7236. Min Act: -0.1700
Data Index: 4109493 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.6611. Min Act: -0.1700
Data Index: 6041640 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.6611. Min Act: -0.1700
Data Index: 8368678 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.6611. Min Act: -0.1700
Data Index: 5760286 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.6924. Min Act: -0.1700
Data Index: 6266921 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.6299. Min Act: -0.1700
Data Index: 7897282 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.6611. Min Act: -0.1700
Data Index: 952866 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5986. Min Act: -0.1700
Data Index: 1000598 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5986. Min Act: -0.1700
Data Index: 7070931 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5674. Min Act: -0.1700
Data Index: 3070927 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5361. Min Act: -0.1700
Data Index: 3185871 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5361. Min Act: -0.1700
Data Index: 6467582 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5361. Min Act: -0.1700
Data Index: 5243315 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5361. Min Act: -0.1700
Data Index: 37451 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5361. Min Act: -0.1700
Data Index: 3515655 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5361. Min Act: -0.1700
Data Index: 6045066 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5049. Min Act: -0.1700
Data Index: 3797195 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5049. Min Act: -0.1700
Data Index: 37452 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7861. Min Range: -5.7861
Max Act: 5.5049. Min Act: -0.1700
Data Index: 5858831 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19