Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2436 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3063. Min Range: -7.3063
Max Act: 7.3063. Min Act: -0.1700
Data Index: 2397729 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3063. Min Range: -7.3063
Max Act: 7.2126. Min Act: -0.1700
Data Index: 6890266 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3063. Min Range: -7.3063
Max Act: 7.2126. Min Act: -0.1700
Data Index: 7231311 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3063. Min Range: -7.3063
Max Act: 7.1188. Min Act: -0.1700
Data Index: 2020539 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3063. Min Range: -7.3063
Max Act: 7.0876. Min Act: -0.1700
Data Index: 2373595 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3063. Min Range: -7.3063
Max Act: 7.0251. Min Act: -0.1700
Data Index: 4278756 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.9938. Min Act: -0.1700
Data Index: 8831902 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3063. Min Range: -7.3063
Max Act: 7.0251. Min Act: -0.1700
Data Index: 65981 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.9626. Min Act: -0.1700
Data Index: 5308591 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.9626. Min Act: -0.1700
Data Index: 8075950 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.9313. Min Act: -0.1700
Data Index: 1300342 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.8376. Min Act: -0.1700
Data Index: 7416802 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.8688. Min Act: -0.1700
Data Index: 3874423 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.8376. Min Act: -0.1700
Data Index: 2020547 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.8376. Min Act: -0.1700
Data Index: 7101947 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.8063. Min Act: -0.1700
Data Index: 7151306 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.7751. Min Act: -0.1700
Data Index: 8366601 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.7751. Min Act: -0.1700
Data Index: 7850249 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.7751. Min Act: -0.1700
Data Index: 7788738 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3063. Min Range: -7.3063
Max Act: 6.7438. Min Act: -0.1700
Data Index: 3817120 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19