Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4453 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.7154. Min Act: -0.1700
Data Index: 6100461 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.5591. Min Act: -0.1700
Data Index: 1205091 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.3091. Min Act: -0.1700
Data Index: 4354254 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.2466. Min Act: -0.1700
Data Index: 3178616 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.2154. Min Act: -0.1700
Data Index: 5495602 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.2154. Min Act: -0.1700
Data Index: 8322815 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.1841. Min Act: -0.1700
Data Index: 8383477 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.1216. Min Act: -0.1700
Data Index: 3567104 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.1216. Min Act: -0.1700
Data Index: 6143316 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.1216. Min Act: -0.1700
Data Index: 854960 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.0904. Min Act: -0.1700
Data Index: 6009286 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.0591. Min Act: -0.1700
Data Index: 4931919 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.0591. Min Act: -0.1700
Data Index: 5000882 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.0591. Min Act: -0.1700
Data Index: 2839752 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.0279. Min Act: -0.1700
Data Index: 2924148 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7154. Min Range: -6.7154
Max Act: 6.0279. Min Act: -0.1700
Data Index: 6787799 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7154. Min Range: -6.7154
Max Act: 5.9966. Min Act: -0.1700
Data Index: 6513774 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7154. Min Range: -6.7154
Max Act: 5.9966. Min Act: -0.1700
Data Index: 7929893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7154. Min Range: -6.7154
Max Act: 5.9654. Min Act: -0.1700
Data Index: 6983103 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7154. Min Range: -6.7154
Max Act: 5.9966. Min Act: -0.1700
Data Index: 7033657 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19