Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.9015. Min Act: -0.1700
Data Index: 633208 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.7140. Min Act: -0.1700
Data Index: 1295074 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.6515. Min Act: -0.1700
Data Index: 4262835 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.5890. Min Act: -0.1700
Data Index: 6723032 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.5265. Min Act: -0.1700
Data Index: 6187715 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.4640. Min Act: -0.1700
Data Index: 1520006 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.4327. Min Act: -0.1700
Data Index: 6550842 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.4327. Min Act: -0.1700
Data Index: 7342381 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.3702. Min Act: -0.1700
Data Index: 7593069 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.3702. Min Act: -0.1700
Data Index: 4613527 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.3390. Min Act: -0.1700
Data Index: 1855684 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.3390. Min Act: -0.1700
Data Index: 5394216 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.3390. Min Act: -0.1700
Data Index: 900799 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.2765. Min Act: -0.1700
Data Index: 4648653 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.3077. Min Act: -0.1700
Data Index: 8779799 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.3390. Min Act: -0.1700
Data Index: 5376877 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.2765. Min Act: -0.1700
Data Index: 2433280 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.2765. Min Act: -0.1700
Data Index: 1034103 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.2765. Min Act: -0.1700
Data Index: 205335 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9015. Min Range: -6.9015
Max Act: 6.2765. Min Act: -0.1700
Data Index: 1563633 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19