Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4907 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.7635. Min Act: -0.1700
Data Index: 7354182 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.5760. Min Act: -0.1700
Data Index: 5362527 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.5135. Min Act: -0.1700
Data Index: 8103974 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.4510. Min Act: -0.1700
Data Index: 5984586 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.3260. Min Act: -0.1700
Data Index: 5900618 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.2635. Min Act: -0.1700
Data Index: 5146078 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.2635. Min Act: -0.1700
Data Index: 733720 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.2635. Min Act: -0.1700
Data Index: 850108 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.2010. Min Act: -0.1700
Data Index: 6654618 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.2010. Min Act: -0.1700
Data Index: 7214545 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.2635. Min Act: -0.1700
Data Index: 4108168 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.1385. Min Act: -0.1700
Data Index: 7278637 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.1385. Min Act: -0.1700
Data Index: 5589953 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.2010. Min Act: -0.1700
Data Index: 7582394 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.1385. Min Act: -0.1700
Data Index: 3858411 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.1385. Min Act: -0.1700
Data Index: 6038612 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.1385. Min Act: -0.1700
Data Index: 4294374 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.0760. Min Act: -0.1700
Data Index: 3937650 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.0760. Min Act: -0.1700
Data Index: 6741163 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7635. Min Range: -8.7635
Max Act: 8.0760. Min Act: -0.1700
Data Index: 4879832 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19