Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1764 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.5668. Min Act: -0.1700
Data Index: 7646696 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.4730. Min Act: -0.1700
Data Index: 5484903 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.5043. Min Act: -0.1700
Data Index: 352692 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.4105. Min Act: -0.1700
Data Index: 2230742 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.4105. Min Act: -0.1700
Data Index: 277703 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.4105. Min Act: -0.1700
Data Index: 157773 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3793. Min Act: -0.1700
Data Index: 1244338 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.4105. Min Act: -0.1700
Data Index: 489641 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3793. Min Act: -0.1700
Data Index: 3282991 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3793. Min Act: -0.1700
Data Index: 6309770 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3793. Min Act: -0.1700
Data Index: 6187359 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3793. Min Act: -0.1700
Data Index: 8668962 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3793. Min Act: -0.1700
Data Index: 4382079 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3480. Min Act: -0.1700
Data Index: 8261043 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3168. Min Act: -0.1700
Data Index: 4822542 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3480. Min Act: -0.1700
Data Index: 2373046 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3793. Min Act: -0.1700
Data Index: 4623521 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3168. Min Act: -0.1700
Data Index: 3098075 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.2855. Min Act: -0.1700
Data Index: 3204336 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.2855. Min Act: -0.1700
Data Index: 1269606 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19