Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3714 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.9634. Min Act: -0.1700
Data Index: 7908643 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.7134. Min Act: -0.1700
Data Index: 3189795 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.7446. Min Act: -0.1700
Data Index: 1040995 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.7446. Min Act: -0.1700
Data Index: 5087898 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.7446. Min Act: -0.1700
Data Index: 6214914 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.7446. Min Act: -0.1700
Data Index: 2614585 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.7134. Min Act: -0.1700
Data Index: 615734 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.6509. Min Act: -0.1700
Data Index: 3818830 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.6509. Min Act: -0.1700
Data Index: 6735284 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.6196. Min Act: -0.1700
Data Index: 1089803 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.6196. Min Act: -0.1700
Data Index: 6738558 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.6196. Min Act: -0.1700
Data Index: 1205412 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.6196. Min Act: -0.1700
Data Index: 388651 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.5884. Min Act: -0.1700
Data Index: 7947058 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.5884. Min Act: -0.1700
Data Index: 3891579 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.5884. Min Act: -0.1700
Data Index: 4345949 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.6196. Min Act: -0.1700
Data Index: 5227653 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.5571. Min Act: -0.1700
Data Index: 1083603 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.5884. Min Act: -0.1700
Data Index: 1202482 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9634. Min Range: -5.9634
Max Act: 5.5884. Min Act: -0.1700
Data Index: 3097378 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19