Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5419 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4720. Min Range: -6.4720
Max Act: 6.4720. Min Act: -0.1700
Data Index: 401372 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4720. Min Range: -6.4720
Max Act: 6.3783. Min Act: -0.1700
Data Index: 4979389 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4720. Min Range: -6.4720
Max Act: 6.2220. Min Act: -0.1700
Data Index: 4979390 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4720. Min Range: -6.4720
Max Act: 6.0970. Min Act: -0.1700
Data Index: 6422207 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4720. Min Range: -6.4720
Max Act: 6.0033. Min Act: -0.1700
Data Index: 6912747 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.9720. Min Act: -0.1700
Data Index: 6158837 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.9408. Min Act: -0.1700
Data Index: 5444229 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.9408. Min Act: -0.1700
Data Index: 4986403 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.9720. Min Act: -0.1700
Data Index: 4038622 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.9095. Min Act: -0.1700
Data Index: 2154328 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.9095. Min Act: -0.1700
Data Index: 1360322 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.9095. Min Act: -0.1700
Data Index: 1344336 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.8783. Min Act: -0.1700
Data Index: 2343189 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.8783. Min Act: -0.1700
Data Index: 1810194 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.8783. Min Act: -0.1700
Data Index: 4782274 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.8470. Min Act: -0.1700
Data Index: 8156786 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.8470. Min Act: -0.1700
Data Index: 557565 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.8158. Min Act: -0.1700
Data Index: 8091299 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.8158. Min Act: -0.1700
Data Index: 4846914 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4720. Min Range: -6.4720
Max Act: 5.8158. Min Act: -0.1700
Data Index: 815662 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19