Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.6866. Min Act: -0.1700
Data Index: 6884300 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.2491. Min Act: -0.1700
Data Index: 1144385 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.1866. Min Act: -0.1700
Data Index: 6400323 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.1866. Min Act: -0.1700
Data Index: 848360 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.1554. Min Act: -0.1700
Data Index: 1165067 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.1554. Min Act: -0.1700
Data Index: 897446 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.1241. Min Act: -0.1700
Data Index: 2438547 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.1241. Min Act: -0.1700
Data Index: 2037476 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.0929. Min Act: -0.1700
Data Index: 1918663 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.1241. Min Act: -0.1700
Data Index: 8795651 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.0929. Min Act: -0.1700
Data Index: 5569173 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.0929. Min Act: -0.1700
Data Index: 672087 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.0304. Min Act: -0.1700
Data Index: 897451 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.0304. Min Act: -0.1700
Data Index: 5937789 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6866. Min Range: -7.6866
Max Act: 7.0304. Min Act: -0.1700
Data Index: 6834135 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6866. Min Range: -7.6866
Max Act: 6.9991. Min Act: -0.1700
Data Index: 6359601 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6866. Min Range: -7.6866
Max Act: 6.9679. Min Act: -0.1700
Data Index: 3270787 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6866. Min Range: -7.6866
Max Act: 6.9679. Min Act: -0.1700
Data Index: 2015766 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6866. Min Range: -7.6866
Max Act: 6.9366. Min Act: -0.1700
Data Index: 4533311 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6866. Min Range: -7.6866
Max Act: 6.9366. Min Act: -0.1700
Data Index: 1080844 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19