Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0023. Min Range: -7.0023
Max Act: 7.0023. Min Act: -0.1700
Data Index: 2678769 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.9398. Min Act: -0.1700
Data Index: 529640 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.8148. Min Act: -0.1700
Data Index: 8273070 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.6585. Min Act: -0.1700
Data Index: 8102010 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5648. Min Act: -0.1700
Data Index: 3455947 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5648. Min Act: -0.1700
Data Index: 5083617 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5648. Min Act: -0.1700
Data Index: 6149573 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5335. Min Act: -0.1700
Data Index: 7567307 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5335. Min Act: -0.1700
Data Index: 2514688 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5335. Min Act: -0.1700
Data Index: 647585 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5023. Min Act: -0.1700
Data Index: 2397365 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5023. Min Act: -0.1700
Data Index: 4225690 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5023. Min Act: -0.1700
Data Index: 1122269 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5023. Min Act: -0.1700
Data Index: 4910594 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5023. Min Act: -0.1700
Data Index: 6736073 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5335. Min Act: -0.1700
Data Index: 8691736 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.4710. Min Act: -0.1700
Data Index: 2144807 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5023. Min Act: -0.1700
Data Index: 2399128 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.5023. Min Act: -0.1700
Data Index: 1323591 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0023. Min Range: -7.0023
Max Act: 6.4710. Min Act: -0.1700
Data Index: 3628575 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19