Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4827 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.5361. Min Act: -0.1700
Data Index: 5327365 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.4736. Min Act: -0.1700
Data Index: 1462018 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.4736. Min Act: -0.1700
Data Index: 6206834 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.4736. Min Act: -0.1700
Data Index: 3643314 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.5048. Min Act: -0.1700
Data Index: 6018351 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.4736. Min Act: -0.1700
Data Index: 3142662 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.4111. Min Act: -0.1700
Data Index: 6094497 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.4111. Min Act: -0.1700
Data Index: 7640428 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3798. Min Act: -0.1700
Data Index: 5518797 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3486. Min Act: -0.1700
Data Index: 1954577 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2861. Min Act: -0.1700
Data Index: 2226366 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3173. Min Act: -0.1700
Data Index: 710183 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2548. Min Act: -0.1700
Data Index: 1076785 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2548. Min Act: -0.1700
Data Index: 4349455 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2861. Min Act: -0.1700
Data Index: 4983222 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2548. Min Act: -0.1700
Data Index: 3805599 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2548. Min Act: -0.1700
Data Index: 2904362 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2548. Min Act: -0.1700
Data Index: 5307091 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2548. Min Act: -0.1700
Data Index: 2946338 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.1923. Min Act: -0.1700
Data Index: 4349445 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19