Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3721 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1683. Min Range: -9.1683
Max Act: 9.1683. Min Act: -0.1700
Data Index: 4686143 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.8558. Min Act: -0.1700
Data Index: 4193250 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.7308. Min Act: -0.1700
Data Index: 2526168 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.6683. Min Act: -0.1700
Data Index: 6308350 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.6058. Min Act: -0.1700
Data Index: 4102711 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.6058. Min Act: -0.1700
Data Index: 7418960 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.6058. Min Act: -0.1700
Data Index: 691968 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.6058. Min Act: -0.1700
Data Index: 783352 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.4808. Min Act: -0.1700
Data Index: 8310246 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.5433. Min Act: -0.1700
Data Index: 7632793 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.4808. Min Act: -0.1700
Data Index: 213428 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.4808. Min Act: -0.1700
Data Index: 7171924 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.4183. Min Act: -0.1700
Data Index: 5799394 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.4183. Min Act: -0.1700
Data Index: 5343081 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.3558. Min Act: -0.1700
Data Index: 3037896 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.3558. Min Act: -0.1700
Data Index: 3543199 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.2933. Min Act: -0.1700
Data Index: 4278990 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.2933. Min Act: -0.1700
Data Index: 3357815 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.2933. Min Act: -0.1700
Data Index: 6128390 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1683. Min Range: -9.1683
Max Act: 8.2933. Min Act: -0.1700
Data Index: 6363789 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19