Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5849 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.7799. Min Act: -0.1700
Data Index: 6460231 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.4986. Min Act: -0.1700
Data Index: 193868 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.2174. Min Act: -0.1700
Data Index: 1974139 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.1861. Min Act: -0.1700
Data Index: 3786286 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.1236. Min Act: -0.1700
Data Index: 4075047 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.1549. Min Act: -0.1700
Data Index: 3686817 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.1549. Min Act: -0.1700
Data Index: 701828 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.1236. Min Act: -0.1700
Data Index: 3582916 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.1236. Min Act: -0.1700
Data Index: 8531178 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.0924. Min Act: -0.1700
Data Index: 3391985 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.0924. Min Act: -0.1700
Data Index: 1187574 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.0924. Min Act: -0.1700
Data Index: 8337365 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7799. Min Range: -6.7799
Max Act: 5.9986. Min Act: -0.1700
Data Index: 1568017 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.0299. Min Act: -0.1700
Data Index: 1687697 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7799. Min Range: -6.7799
Max Act: 6.0299. Min Act: -0.1700
Data Index: 7685723 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7799. Min Range: -6.7799
Max Act: 5.9986. Min Act: -0.1700
Data Index: 2198054 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7799. Min Range: -6.7799
Max Act: 5.9986. Min Act: -0.1700
Data Index: 5479302 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7799. Min Range: -6.7799
Max Act: 5.9986. Min Act: -0.1700
Data Index: 8148658 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7799. Min Range: -6.7799
Max Act: 5.9674. Min Act: -0.1700
Data Index: 8624352 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7799. Min Range: -6.7799
Max Act: 5.9674. Min Act: -0.1700
Data Index: 6180229 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19