Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3961 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0144. Min Range: -9.0144
Max Act: 9.0144. Min Act: -0.1700
Data Index: 4839220 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.8894. Min Act: -0.1700
Data Index: 7918602 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.8894. Min Act: -0.1700
Data Index: 695219 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.8269. Min Act: -0.1700
Data Index: 8737157 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.8269. Min Act: -0.1700
Data Index: 4872609 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.7644. Min Act: -0.1700
Data Index: 4829360 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.7019. Min Act: -0.1700
Data Index: 6287453 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.5769. Min Act: -0.1700
Data Index: 940760 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.5144. Min Act: -0.1700
Data Index: 37119 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.4519. Min Act: -0.1700
Data Index: 2648625 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.3894. Min Act: -0.1700
Data Index: 932175 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.3894. Min Act: -0.1700
Data Index: 7655514 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.3269. Min Act: -0.1700
Data Index: 19975 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.3269. Min Act: -0.1700
Data Index: 4407988 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.3269. Min Act: -0.1700
Data Index: 6416445 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.3269. Min Act: -0.1700
Data Index: 6925816 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.2644. Min Act: -0.1700
Data Index: 636400 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.2644. Min Act: -0.1700
Data Index: 7631867 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.2644. Min Act: -0.1700
Data Index: 5194469 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0144. Min Range: -9.0144
Max Act: 8.2644. Min Act: -0.1700
Data Index: 4262783 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19