Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1992 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0130. Min Range: -7.0130
Max Act: 7.0130. Min Act: -0.1700
Data Index: 6686459 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.9505. Min Act: -0.1700
Data Index: 2615439 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.9505. Min Act: -0.1700
Data Index: 4407572 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.8880. Min Act: -0.1700
Data Index: 417315 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.8880. Min Act: -0.1700
Data Index: 5740205 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.8568. Min Act: -0.1700
Data Index: 7162919 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.8568. Min Act: -0.1700
Data Index: 8515343 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.8255. Min Act: -0.1700
Data Index: 7187487 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.7943. Min Act: -0.1700
Data Index: 3080752 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.7005. Min Act: -0.1700
Data Index: 8270606 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.7318. Min Act: -0.1700
Data Index: 5827552 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.7318. Min Act: -0.1700
Data Index: 3516020 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.7005. Min Act: -0.1700
Data Index: 4871258 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.7005. Min Act: -0.1700
Data Index: 7430947 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.6693. Min Act: -0.1700
Data Index: 2827930 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.6380. Min Act: -0.1700
Data Index: 2712008 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.6693. Min Act: -0.1700
Data Index: 2588712 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.6380. Min Act: -0.1700
Data Index: 5821038 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.5755. Min Act: -0.1700
Data Index: 958979 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0130. Min Range: -7.0130
Max Act: 6.6068. Min Act: -0.1700
Data Index: 4927912 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19