Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5492. Min Range: -7.5492
Max Act: 7.5492. Min Act: -0.1700
Data Index: 5532142 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.6117. Min Act: -0.1700
Data Index: 1952455 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.5804. Min Act: -0.1700
Data Index: 6940122 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.5492. Min Act: -0.1700
Data Index: 5053858 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.4554. Min Act: -0.1700
Data Index: 8063318 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.4554. Min Act: -0.1700
Data Index: 3497370 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.4554. Min Act: -0.1700
Data Index: 6684240 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.3617. Min Act: -0.1700
Data Index: 8415160 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.3617. Min Act: -0.1700
Data Index: 3755440 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.3617. Min Act: -0.1700
Data Index: 5057365 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.2679. Min Act: -0.1700
Data Index: 6156797 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.2679. Min Act: -0.1700
Data Index: 6384065 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.2367. Min Act: -0.1700
Data Index: 476354 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.2054. Min Act: -0.1700
Data Index: 5271586 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.2367. Min Act: -0.1700
Data Index: 6388020 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.2367. Min Act: -0.1700
Data Index: 3237391 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.2367. Min Act: -0.1700
Data Index: 1613765 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.2054. Min Act: -0.1700
Data Index: 1909635 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.1742. Min Act: -0.1700
Data Index: 4042694 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5492. Min Range: -7.5492
Max Act: 6.1429. Min Act: -0.1700
Data Index: 3004974 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19