Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1560 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.4962. Min Act: -0.1700
Data Index: 8654670 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.3399. Min Act: -0.1700
Data Index: 4747321 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.4024. Min Act: -0.1700
Data Index: 5680776 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.3087. Min Act: -0.1700
Data Index: 3365387 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.1837. Min Act: -0.1700
Data Index: 7752650 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.1837. Min Act: -0.1700
Data Index: 5512463 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.1212. Min Act: -0.1700
Data Index: 996560 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.1524. Min Act: -0.1700
Data Index: 8219075 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.1212. Min Act: -0.1700
Data Index: 7051378 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.1212. Min Act: -0.1700
Data Index: 6422649 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.1212. Min Act: -0.1700
Data Index: 3431155 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.1524. Min Act: -0.1700
Data Index: 3138565 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.0899. Min Act: -0.1700
Data Index: 6422648 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.0899. Min Act: -0.1700
Data Index: 6719761 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.0899. Min Act: -0.1700
Data Index: 4932212 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.0587. Min Act: -0.1700
Data Index: 489482 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.0587. Min Act: -0.1700
Data Index: 8691307 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.0274. Min Act: -0.1700
Data Index: 5495568 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4962. Min Range: -5.4962
Max Act: 5.0274. Min Act: -0.1700
Data Index: 5514760 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4962. Min Range: -5.4962
Max Act: 4.9962. Min Act: -0.1700
Data Index: 4112492 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19