Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2822. Min Range: -7.2822
Max Act: 7.2822. Min Act: -0.1700
Data Index: 5755110 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2822. Min Range: -7.2822
Max Act: 7.0322. Min Act: -0.1700
Data Index: 1985317 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.9697. Min Act: -0.1700
Data Index: 807821 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.9072. Min Act: -0.1700
Data Index: 6946478 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.8760. Min Act: -0.1700
Data Index: 8263782 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.8135. Min Act: -0.1700
Data Index: 6554271 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.7510. Min Act: -0.1700
Data Index: 5297126 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.7197. Min Act: -0.1700
Data Index: 1931315 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.7197. Min Act: -0.1700
Data Index: 3426780 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.6885. Min Act: -0.1700
Data Index: 3016039 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.6885. Min Act: -0.1700
Data Index: 3083049 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.6885. Min Act: -0.1700
Data Index: 5461585 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.6885. Min Act: -0.1700
Data Index: 1485660 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.6260. Min Act: -0.1700
Data Index: 8684838 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.6260. Min Act: -0.1700
Data Index: 5286957 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.5947. Min Act: -0.1700
Data Index: 531684 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.5947. Min Act: -0.1700
Data Index: 499230 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.5947. Min Act: -0.1700
Data Index: 5442909 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.5947. Min Act: -0.1700
Data Index: 7380520 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2822. Min Range: -7.2822
Max Act: 6.5635. Min Act: -0.1700
Data Index: 7009896 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19