Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5926 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.4026. Min Act: -0.1700
Data Index: 4062474 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.3088. Min Act: -0.1700
Data Index: 1181289 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.2151. Min Act: -0.1700
Data Index: 5166993 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.1838. Min Act: -0.1700
Data Index: 23164 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.1838. Min Act: -0.1700
Data Index: 5993301 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.1526. Min Act: -0.1700
Data Index: 5473598 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.1526. Min Act: -0.1700
Data Index: 5993305 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.0588. Min Act: -0.1700
Data Index: 2720653 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.0901. Min Act: -0.1700
Data Index: 8260970 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.0588. Min Act: -0.1700
Data Index: 4994125 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.0588. Min Act: -0.1700
Data Index: 8792512 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.0588. Min Act: -0.1700
Data Index: 387360 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.0588. Min Act: -0.1700
Data Index: 7029458 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.0276. Min Act: -0.1700
Data Index: 8273271 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9963. Min Act: -0.1700
Data Index: 7800426 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9651. Min Act: -0.1700
Data Index: 2785215 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9963. Min Act: -0.1700
Data Index: 571886 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9963. Min Act: -0.1700
Data Index: 6038500 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9651. Min Act: -0.1700
Data Index: 2692787 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9338. Min Act: -0.1700
Data Index: 2906921 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19