Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.2915. Min Act: -0.1700
Data Index: 966131 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.2289. Min Act: -0.1700
Data Index: 7140110 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.1664. Min Act: -0.1700
Data Index: 8125824 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.1352. Min Act: -0.1700
Data Index: 5528291 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.1352. Min Act: -0.1700
Data Index: 973800 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.1039. Min Act: -0.1700
Data Index: 1420420 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.1352. Min Act: -0.1700
Data Index: 2700563 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.1039. Min Act: -0.1700
Data Index: 7562064 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.0727. Min Act: -0.1700
Data Index: 4558692 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.0727. Min Act: -0.1700
Data Index: 1210033 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.0414. Min Act: -0.1700
Data Index: 2565815 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.0414. Min Act: -0.1700
Data Index: 3492503 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.0101. Min Act: -0.1700
Data Index: 2028046 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.0414. Min Act: -0.1700
Data Index: 1677114 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2915. Min Range: -4.2915
Max Act: 4.0101. Min Act: -0.1700
Data Index: 6777261 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2915. Min Range: -4.2915
Max Act: 3.9789. Min Act: -0.1700
Data Index: 2416013 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2915. Min Range: -4.2915
Max Act: 3.9789. Min Act: -0.1700
Data Index: 2004683 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2915. Min Range: -4.2915
Max Act: 3.9789. Min Act: -0.1700
Data Index: 1548294 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2915. Min Range: -4.2915
Max Act: 3.9789. Min Act: -0.1700
Data Index: 5597414 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2915. Min Range: -4.2915
Max Act: 3.9789. Min Act: -0.1700
Data Index: 4087097 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19