Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4574 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3255. Min Range: -6.3255
Max Act: 6.3255. Min Act: -0.1700
Data Index: 443044 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3255. Min Range: -6.3255
Max Act: 6.1380. Min Act: -0.1700
Data Index: 2875935 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3255. Min Range: -6.3255
Max Act: 6.0130. Min Act: -0.1700
Data Index: 4014576 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.9818. Min Act: -0.1700
Data Index: 8809799 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.8880. Min Act: -0.1700
Data Index: 150714 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.8880. Min Act: -0.1700
Data Index: 6493275 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.8568. Min Act: -0.1700
Data Index: 1680915 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.8255. Min Act: -0.1700
Data Index: 3452054 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.8568. Min Act: -0.1699
Data Index: 6774708 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.8568. Min Act: -0.1700
Data Index: 163876 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.8255. Min Act: -0.1700
Data Index: 2071295 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.7943. Min Act: -0.1700
Data Index: 200079 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.7943. Min Act: -0.1700
Data Index: 6168097 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.7630. Min Act: -0.1700
Data Index: 2856400 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.7630. Min Act: -0.1700
Data Index: 786768 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.7630. Min Act: -0.1700
Data Index: 2686992 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.7318. Min Act: -0.1700
Data Index: 6483398 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.6693. Min Act: -0.1700
Data Index: 8261795 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.6693. Min Act: -0.1700
Data Index: 491213 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3255. Min Range: -6.3255
Max Act: 5.6693. Min Act: -0.1700
Data Index: 3998089 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19