Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.9639. Min Act: -0.1700
Data Index: 4570444 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.8389. Min Act: -0.1700
Data Index: 6856237 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.7139. Min Act: -0.1700
Data Index: 4612646 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.6514. Min Act: -0.1700
Data Index: 7677904 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.5889. Min Act: -0.1700
Data Index: 2415492 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.3389. Min Act: -0.1700
Data Index: 8619532 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.3389. Min Act: -0.1700
Data Index: 2170509 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.4014. Min Act: -0.1700
Data Index: 4719488 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.3389. Min Act: -0.1700
Data Index: 5526092 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.2764. Min Act: -0.1700
Data Index: 3843331 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.3389. Min Act: -0.1700
Data Index: 989932 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.2764. Min Act: -0.1700
Data Index: 2864637 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.2139. Min Act: -0.1700
Data Index: 8796859 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.2139. Min Act: -0.1700
Data Index: 7165083 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.1514. Min Act: -0.1700
Data Index: 773643 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.1514. Min Act: -0.1700
Data Index: 2346352 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.1514. Min Act: -0.1700
Data Index: 4006066 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.1514. Min Act: -0.1700
Data Index: 8103706 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.1514. Min Act: -0.1700
Data Index: 7412608 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9639. Min Range: -8.9639
Max Act: 8.1514. Min Act: -0.1700
Data Index: 7958645 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19