Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3819 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1898. Min Range: -6.1898
Max Act: 6.1898. Min Act: -0.1700
Data Index: 7583164 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1898. Min Range: -6.1898
Max Act: 6.1586. Min Act: -0.1700
Data Index: 705968 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1898. Min Range: -6.1898
Max Act: 6.0961. Min Act: -0.1700
Data Index: 4474561 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1898. Min Range: -6.1898
Max Act: 6.0336. Min Act: -0.1700
Data Index: 4094233 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1898. Min Range: -6.1898
Max Act: 6.0023. Min Act: -0.1700
Data Index: 6473790 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.9398. Min Act: -0.1700
Data Index: 8712510 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.8773. Min Act: -0.1700
Data Index: 5433158 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.8773. Min Act: -0.1700
Data Index: 2758479 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.8148. Min Act: -0.1700
Data Index: 3494768 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.8461. Min Act: -0.1700
Data Index: 884527 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.7836. Min Act: -0.1700
Data Index: 6525916 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.7523. Min Act: -0.1700
Data Index: 5638299 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.7523. Min Act: -0.1700
Data Index: 4145699 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.7211. Min Act: -0.1700
Data Index: 4998991 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.6586. Min Act: -0.1700
Data Index: 3230404 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.6898. Min Act: -0.1700
Data Index: 7373168 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.6898. Min Act: -0.1700
Data Index: 6191660 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.6273. Min Act: -0.1700
Data Index: 2485943 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.6273. Min Act: -0.1700
Data Index: 7205076 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1898. Min Range: -6.1898
Max Act: 5.6273. Min Act: -0.1700
Data Index: 1394613 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19