Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5786 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.3527. Min Act: -0.1700
Data Index: 2544131 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.1965. Min Act: -0.1700
Data Index: 3662908 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.1965. Min Act: -0.1700
Data Index: 3348666 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.1652. Min Act: -0.1700
Data Index: 6445706 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.1027. Min Act: -0.1700
Data Index: 96499 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.1027. Min Act: -0.1700
Data Index: 4524339 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 5322629 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 7229998 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 7110613 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 1749284 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 5998110 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.0715. Min Act: -0.1700
Data Index: 8629045 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.0090. Min Act: -0.1700
Data Index: 7691834 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3527. Min Range: -7.3527
Max Act: 7.0090. Min Act: -0.1700
Data Index: 4782418 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3527. Min Range: -7.3527
Max Act: 6.9777. Min Act: -0.1700
Data Index: 7846924 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3527. Min Range: -7.3527
Max Act: 6.9777. Min Act: -0.1700
Data Index: 1582273 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3527. Min Range: -7.3527
Max Act: 6.9465. Min Act: -0.1700
Data Index: 7410875 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3527. Min Range: -7.3527
Max Act: 6.9152. Min Act: -0.1700
Data Index: 2388531 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3527. Min Range: -7.3527
Max Act: 6.9152. Min Act: -0.1700
Data Index: 2495572 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3527. Min Range: -7.3527
Max Act: 6.9152. Min Act: -0.1700
Data Index: 4521053 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19