Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.5000. Min Act: -0.1700
Data Index: 7736866 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.4063. Min Act: -0.1700
Data Index: 8214718 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.3125. Min Act: -0.1700
Data Index: 6893748 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.2813. Min Act: -0.1700
Data Index: 192205 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.3438. Min Act: -0.1700
Data Index: 535817 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.1875. Min Act: -0.1700
Data Index: 1245410 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.1563. Min Act: -0.1700
Data Index: 3526761 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.1563. Min Act: -0.1700
Data Index: 2641966 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.1563. Min Act: -0.1700
Data Index: 5367560 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.1563. Min Act: -0.1700
Data Index: 6318716 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.1563. Min Act: -0.1700
Data Index: 3053281 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.1250. Min Act: -0.1700
Data Index: 4283780 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.1250. Min Act: -0.1700
Data Index: 599422 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.0625. Min Act: -0.1700
Data Index: 3289728 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.0938. Min Act: -0.1700
Data Index: 6121277 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.0938. Min Act: -0.1700
Data Index: 2982767 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.0938. Min Act: -0.1700
Data Index: 2707918 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.0938. Min Act: -0.1700
Data Index: 2963676 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.0938. Min Act: -0.1700
Data Index: 3251182 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5000. Min Range: -7.5000
Max Act: 7.0625. Min Act: -0.1700
Data Index: 2021383 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19