Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4697 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4804. Min Range: -9.4804
Max Act: 9.4804. Min Act: -0.1700
Data Index: 4355465 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4804. Min Range: -9.4804
Max Act: 9.2304. Min Act: -0.1700
Data Index: 6696122 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.7929. Min Act: -0.1700
Data Index: 1100536 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.7304. Min Act: -0.1700
Data Index: 7798023 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.6679. Min Act: -0.1700
Data Index: 8252848 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.6054. Min Act: -0.1700
Data Index: 3576321 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.6054. Min Act: -0.1700
Data Index: 5424368 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.5429. Min Act: -0.1700
Data Index: 6745535 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.6054. Min Act: -0.1700
Data Index: 1429513 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.5429. Min Act: -0.1700
Data Index: 5680693 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.5429. Min Act: -0.1700
Data Index: 6140231 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.5429. Min Act: -0.1700
Data Index: 6594011 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.4804. Min Act: -0.1700
Data Index: 3362863 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.5429. Min Act: -0.1700
Data Index: 8173202 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.4179. Min Act: -0.1700
Data Index: 7417324 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.4804. Min Act: -0.1700
Data Index: 3851663 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.4179. Min Act: -0.1700
Data Index: 4220065 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.4179. Min Act: -0.1700
Data Index: 2813716 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.3554. Min Act: -0.1700
Data Index: 5816474 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4804. Min Range: -9.4804
Max Act: 8.3554. Min Act: -0.1700
Data Index: 313511 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19