Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.5012. Min Act: -0.1700
Data Index: 7512521 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.3449. Min Act: -0.1700
Data Index: 6199394 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.3449. Min Act: -0.1700
Data Index: 2844874 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.2512. Min Act: -0.1700
Data Index: 3301430 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.2824. Min Act: -0.1700
Data Index: 6445268 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.2824. Min Act: -0.1700
Data Index: 2961001 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.2824. Min Act: -0.1700
Data Index: 6199398 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.2199. Min Act: -0.1700
Data Index: 6296358 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.1887. Min Act: -0.1700
Data Index: 613441 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.1574. Min Act: -0.1700
Data Index: 3581582 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.1574. Min Act: -0.1700
Data Index: 6445266 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.1574. Min Act: -0.1700
Data Index: 7485740 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.1262. Min Act: -0.1700
Data Index: 6199396 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.1262. Min Act: -0.1700
Data Index: 4478418 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.0949. Min Act: -0.1700
Data Index: 4928523 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.0949. Min Act: -0.1700
Data Index: 2001205 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.0637. Min Act: -0.1700
Data Index: 6825727 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.0949. Min Act: -0.1700
Data Index: 1889005 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.0324. Min Act: -0.1700
Data Index: 2237889 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5012. Min Range: -6.5012
Max Act: 6.0637. Min Act: -0.1700
Data Index: 3998417 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19