Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.8517. Min Act: -0.1700
Data Index: 1825851 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.7736. Min Act: -0.1700
Data Index: 4964886 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.7110. Min Act: -0.1700
Data Index: 8208806 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.6797. Min Act: -0.1700
Data Index: 7675250 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.6797. Min Act: -0.1700
Data Index: 5494662 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.6484. Min Act: -0.1700
Data Index: 1388697 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.6171. Min Act: -0.1700
Data Index: 1272010 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.6171. Min Act: -0.1700
Data Index: 4367776 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.6015. Min Act: -0.1700
Data Index: 6815505 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.5858. Min Act: -0.1700
Data Index: 4312809 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.5702. Min Act: -0.1700
Data Index: 3487003 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.5232. Min Act: -0.1700
Data Index: 1584821 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.4919. Min Act: -0.1700
Data Index: 3954168 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.5232. Min Act: -0.1700
Data Index: 2606995 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.4919. Min Act: -0.1700
Data Index: 1690357 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.4919. Min Act: -0.1700
Data Index: 2125301 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.4919. Min Act: -0.1700
Data Index: 2069984 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.4919. Min Act: -0.1700
Data Index: 1607044 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.4919. Min Act: -0.1700
Data Index: 8747811 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8517. Min Range: -3.8517
Max Act: 3.4762. Min Act: -0.1700
Data Index: 6516591 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19