Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 675 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.2284. Min Act: -0.1700
Data Index: 7748483 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.2284. Min Act: -0.1700
Data Index: 1767594 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.2597. Min Act: -0.1700
Data Index: 1254282 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.2284. Min Act: -0.1700
Data Index: 8692391 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1972. Min Act: -0.1700
Data Index: 1532070 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1659. Min Act: -0.1700
Data Index: 4277649 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1347. Min Act: -0.1700
Data Index: 4529300 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1347. Min Act: -0.1700
Data Index: 6408633 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1347. Min Act: -0.1700
Data Index: 6763901 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1347. Min Act: -0.1700
Data Index: 2830200 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1034. Min Act: -0.1700
Data Index: 873395 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1034. Min Act: -0.1700
Data Index: 3200973 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1034. Min Act: -0.1700
Data Index: 4767181 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1034. Min Act: -0.1700
Data Index: 5722934 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1034. Min Act: -0.1700
Data Index: 2231085 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.1034. Min Act: -0.1700
Data Index: 6991814 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.0722. Min Act: -0.1700
Data Index: 3567878 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.0722. Min Act: -0.1700
Data Index: 3641242 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.0722. Min Act: -0.1700
Data Index: 2773486 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2597. Min Range: -5.2597
Max Act: 5.0722. Min Act: -0.1700
Data Index: 6031860 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19