Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 165 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.3852. Min Act: -0.1700
Data Index: 1090836 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.3227. Min Act: -0.1700
Data Index: 8071011 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.3227. Min Act: -0.1700
Data Index: 290693 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.2915. Min Act: -0.1700
Data Index: 8780073 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.1352. Min Act: -0.1700
Data Index: 7057234 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.1040. Min Act: -0.1700
Data Index: 5322610 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.1040. Min Act: -0.1700
Data Index: 993625 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.0727. Min Act: -0.1700
Data Index: 4226840 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.0415. Min Act: -0.1700
Data Index: 1500824 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.0102. Min Act: -0.1700
Data Index: 4738540 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.9477. Min Act: -0.1700
Data Index: 927982 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.9790. Min Act: -0.1700
Data Index: 8456519 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.9165. Min Act: -0.1700
Data Index: 5559711 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.9165. Min Act: -0.1700
Data Index: 8172706 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.9165. Min Act: -0.1700
Data Index: 7227196 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.8852. Min Act: -0.1700
Data Index: 7516632 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.8852. Min Act: -0.1700
Data Index: 559132 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.8540. Min Act: -0.1700
Data Index: 2257274 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.8540. Min Act: -0.1700
Data Index: 8559793 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.8227. Min Act: -0.1700
Data Index: 1154674 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19