Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0088. Min Range: -9.0088
Max Act: 9.0088. Min Act: -0.1700
Data Index: 3920698 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.7588. Min Act: -0.1700
Data Index: 7635893 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.7588. Min Act: -0.1700
Data Index: 349947 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.7588. Min Act: -0.1700
Data Index: 4834006 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.6963. Min Act: -0.1700
Data Index: 6724563 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.6963. Min Act: -0.1700
Data Index: 4744699 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.6338. Min Act: -0.1700
Data Index: 7303764 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.5713. Min Act: -0.1700
Data Index: 3156373 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.5713. Min Act: -0.1700
Data Index: 1606902 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.5713. Min Act: -0.1700
Data Index: 8039645 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.5713. Min Act: -0.1700
Data Index: 7712365 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.5088. Min Act: -0.1700
Data Index: 1423974 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.5088. Min Act: -0.1700
Data Index: 1600628 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.5088. Min Act: -0.1700
Data Index: 6297463 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.5088. Min Act: -0.1700
Data Index: 1507100 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.4463. Min Act: -0.1700
Data Index: 7449116 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.4463. Min Act: -0.1700
Data Index: 2762099 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.4463. Min Act: -0.1700
Data Index: 185336 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.4463. Min Act: -0.1700
Data Index: 848414 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0088. Min Range: -9.0088
Max Act: 8.4463. Min Act: -0.1700
Data Index: 2429732 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19