Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2280 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1047. Min Range: -7.1047
Max Act: 7.1047. Min Act: -0.1700
Data Index: 5831798 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1047. Min Range: -7.1047
Max Act: 7.0109. Min Act: -0.1700
Data Index: 708648 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.7609. Min Act: -0.1700
Data Index: 5211746 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.7297. Min Act: -0.1700
Data Index: 1580379 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6984. Min Act: -0.1700
Data Index: 6149558 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.7297. Min Act: -0.1700
Data Index: 5440253 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6984. Min Act: -0.1700
Data Index: 2388014 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6984. Min Act: -0.1700
Data Index: 2371948 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6672. Min Act: -0.1700
Data Index: 2410843 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6672. Min Act: -0.1700
Data Index: 8234732 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6359. Min Act: -0.1700
Data Index: 5864218 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6359. Min Act: -0.1700
Data Index: 5124306 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6047. Min Act: -0.1700
Data Index: 8484449 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6359. Min Act: -0.1700
Data Index: 3913849 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6047. Min Act: -0.1700
Data Index: 7931572 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.5734. Min Act: -0.1700
Data Index: 7468444 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.5734. Min Act: -0.1700
Data Index: 4646678 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.5734. Min Act: -0.1700
Data Index: 7134514 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.5422. Min Act: -0.1700
Data Index: 2157636 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.5422. Min Act: -0.1700
Data Index: 7983132 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19