Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.6731. Min Act: -0.1700
Data Index: 2846464 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.6731. Min Act: -0.1700
Data Index: 4912077 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.5794. Min Act: -0.1700
Data Index: 4707897 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.5481. Min Act: -0.1700
Data Index: 6393851 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.5169. Min Act: -0.1700
Data Index: 659938 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.4856. Min Act: -0.1700
Data Index: 2426125 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.4856. Min Act: -0.1700
Data Index: 5983725 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.4231. Min Act: -0.1700
Data Index: 3644652 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.4231. Min Act: -0.1700
Data Index: 6590024 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.4231. Min Act: -0.1700
Data Index: 5215528 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.4231. Min Act: -0.1700
Data Index: 7812789 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.3919. Min Act: -0.1700
Data Index: 3167847 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.3919. Min Act: -0.1700
Data Index: 2458462 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.3294. Min Act: -0.1700
Data Index: 7057691 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.3606. Min Act: -0.1700
Data Index: 452877 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.3606. Min Act: -0.1700
Data Index: 1248400 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.3294. Min Act: -0.1700
Data Index: 993072 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.3294. Min Act: -0.1700
Data Index: 3249233 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.3294. Min Act: -0.1700
Data Index: 1468586 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6731. Min Range: -5.6731
Max Act: 5.3294. Min Act: -0.1700
Data Index: 5294653 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19