Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4120 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3042. Min Range: -8.3042
Max Act: 8.3042. Min Act: -0.1700
Data Index: 1380910 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3042. Min Range: -8.3042
Max Act: 8.3042. Min Act: -0.1700
Data Index: 4007388 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3042. Min Range: -8.3042
Max Act: 8.1792. Min Act: -0.1700
Data Index: 7748318 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3042. Min Range: -8.3042
Max Act: 8.1792. Min Act: -0.1700
Data Index: 2156135 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3042. Min Range: -8.3042
Max Act: 8.0542. Min Act: -0.1700
Data Index: 77198 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.9292. Min Act: -0.1700
Data Index: 3646766 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.9917. Min Act: -0.1700
Data Index: 4981987 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.9292. Min Act: -0.1700
Data Index: 4032881 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8667. Min Act: -0.1700
Data Index: 6732810 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8667. Min Act: -0.1700
Data Index: 3034804 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8667. Min Act: -0.1700
Data Index: 6720438 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8667. Min Act: -0.1700
Data Index: 7439863 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8042. Min Act: -0.1700
Data Index: 5930188 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8042. Min Act: -0.1700
Data Index: 433937 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8042. Min Act: -0.1700
Data Index: 8755927 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8042. Min Act: -0.1700
Data Index: 2512491 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8042. Min Act: -0.1700
Data Index: 3397100 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.8042. Min Act: -0.1700
Data Index: 3465834 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.7417. Min Act: -0.1700
Data Index: 1739017 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3042. Min Range: -8.3042
Max Act: 7.7417. Min Act: -0.1700
Data Index: 3025160 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19