Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5702 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0918. Min Range: -4.0918
Max Act: 4.0918. Min Act: -0.1700
Data Index: 6580862 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0918. Min Range: -4.0918
Max Act: 4.0293. Min Act: -0.1700
Data Index: 6129993 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0918. Min Range: -4.0918
Max Act: 4.0293. Min Act: -0.1700
Data Index: 4457853 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0918. Min Range: -4.0918
Max Act: 4.0293. Min Act: -0.1700
Data Index: 5080190 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.9980. Min Act: -0.1700
Data Index: 3055443 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.9355. Min Act: -0.1700
Data Index: 8598744 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.9042. Min Act: -0.1700
Data Index: 6740124 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.9042. Min Act: -0.1700
Data Index: 283089 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.9355. Min Act: -0.1700
Data Index: 3278447 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.8417. Min Act: -0.1700
Data Index: 2030876 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.8417. Min Act: -0.1700
Data Index: 4977334 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.8417. Min Act: -0.1700
Data Index: 5080192 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.8417. Min Act: -0.1700
Data Index: 3706808 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.8104. Min Act: -0.1700
Data Index: 1311217 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.8104. Min Act: -0.1700
Data Index: 3986758 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.8104. Min Act: -0.1700
Data Index: 179937 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.7792. Min Act: -0.1700
Data Index: 1118866 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.7792. Min Act: -0.1700
Data Index: 4774135 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.7792. Min Act: -0.1700
Data Index: 829071 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0918. Min Range: -4.0918
Max Act: 3.7792. Min Act: -0.1700
Data Index: 4729961 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19