Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5643 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.8433. Min Act: -0.1700
Data Index: 6372215 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.5933. Min Act: -0.1700
Data Index: 6567434 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.5933. Min Act: -0.1700
Data Index: 7638603 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.5308. Min Act: -0.1700
Data Index: 3219234 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.4995. Min Act: -0.1700
Data Index: 1615813 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.4995. Min Act: -0.1700
Data Index: 549229 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.4995. Min Act: -0.1700
Data Index: 24820 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.4370. Min Act: -0.1700
Data Index: 317826 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.3745. Min Act: -0.1700
Data Index: 2487139 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.4058. Min Act: -0.1700
Data Index: 2891943 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.4058. Min Act: -0.1700
Data Index: 7497660 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.4058. Min Act: -0.1700
Data Index: 2660138 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.3433. Min Act: -0.1700
Data Index: 5564880 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.3433. Min Act: -0.1700
Data Index: 6055745 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.2808. Min Act: -0.1700
Data Index: 4972229 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.3120. Min Act: -0.1700
Data Index: 5742392 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.2808. Min Act: -0.1700
Data Index: 7073194 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.3433. Min Act: -0.1700
Data Index: 6694790 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.3120. Min Act: -0.1700
Data Index: 3861026 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8433. Min Range: -6.8433
Max Act: 6.2808. Min Act: -0.1700
Data Index: 5572496 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19