Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1193 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2971. Min Range: -8.2971
Max Act: 8.2971. Min Act: -0.1700
Data Index: 1403939 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.7971. Min Act: -0.1700
Data Index: 6011479 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.6721. Min Act: -0.1700
Data Index: 7298432 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.5783. Min Act: -0.1700
Data Index: 2605969 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.5471. Min Act: -0.1700
Data Index: 1836307 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.4846. Min Act: -0.1700
Data Index: 1507234 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.4846. Min Act: -0.1700
Data Index: 1934102 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.4533. Min Act: -0.1700
Data Index: 455120 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.3908. Min Act: -0.1700
Data Index: 1983776 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.3908. Min Act: -0.1700
Data Index: 1832805 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.3283. Min Act: -0.1700
Data Index: 442198 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.3283. Min Act: -0.1700
Data Index: 987691 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.2033. Min Act: -0.1700
Data Index: 720014 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.2346. Min Act: -0.1700
Data Index: 5557610 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.2346. Min Act: -0.1700
Data Index: 1925376 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.2346. Min Act: -0.1700
Data Index: 1215918 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.2346. Min Act: -0.1700
Data Index: 5780717 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.2346. Min Act: -0.1700
Data Index: 1072877 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.2346. Min Act: -0.1700
Data Index: 652983 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2971. Min Range: -8.2971
Max Act: 7.2346. Min Act: -0.1700
Data Index: 500621 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19