Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0587. Min Range: -7.0587
Max Act: 7.0587. Min Act: -0.1700
Data Index: 8698176 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.8400. Min Act: -0.1700
Data Index: 4273296 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.7150. Min Act: -0.1700
Data Index: 777739 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.5900. Min Act: -0.1700
Data Index: 6544925 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.5587. Min Act: -0.1700
Data Index: 2582976 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.5275. Min Act: -0.1700
Data Index: 1819459 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.4962. Min Act: -0.1700
Data Index: 6785884 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.4962. Min Act: -0.1700
Data Index: 1774886 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.4337. Min Act: -0.1700
Data Index: 2231654 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.4337. Min Act: -0.1700
Data Index: 6191327 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.4025. Min Act: -0.1700
Data Index: 5367630 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.4025. Min Act: -0.1700
Data Index: 6189292 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.3712. Min Act: -0.1700
Data Index: 3130953 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.4025. Min Act: -0.1700
Data Index: 6694362 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.4025. Min Act: -0.1700
Data Index: 6737475 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.3712. Min Act: -0.1700
Data Index: 3718370 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.3087. Min Act: -0.1700
Data Index: 1597871 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.3087. Min Act: -0.1700
Data Index: 8090518 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.3087. Min Act: -0.1700
Data Index: 7502818 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0587. Min Range: -7.0587
Max Act: 6.3087. Min Act: -0.1700
Data Index: 8559146 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19