Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.8667. Min Act: -0.1700
Data Index: 2918602 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7417. Min Act: -0.1700
Data Index: 3968732 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7104. Min Act: -0.1700
Data Index: 7638750 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7104. Min Act: -0.1700
Data Index: 2982845 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7104. Min Act: -0.1700
Data Index: 2727784 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6792. Min Act: -0.1700
Data Index: 3965245 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6792. Min Act: -0.1700
Data Index: 6183551 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6167. Min Act: -0.1700
Data Index: 7690096 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6167. Min Act: -0.1700
Data Index: 3802874 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6167. Min Act: -0.1700
Data Index: 23179 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6167. Min Act: -0.1700
Data Index: 282339 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5854. Min Act: -0.1700
Data Index: 3590709 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5854. Min Act: -0.1700
Data Index: 8790593 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5854. Min Act: -0.1700
Data Index: 8625385 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5542. Min Act: -0.1700
Data Index: 5885092 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5542. Min Act: -0.1700
Data Index: 1502038 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5542. Min Act: -0.1700
Data Index: 8431080 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5229. Min Act: -0.1700
Data Index: 3693776 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5229. Min Act: -0.1700
Data Index: 1738269 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5229. Min Act: -0.1700
Data Index: 6414561 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19