Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 833 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1409. Min Range: -9.1409
Max Act: 9.1409. Min Act: -0.1700
Data Index: 2993535 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1409. Min Range: -9.1409
Max Act: 9.0784. Min Act: -0.1700
Data Index: 850013 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1409. Min Range: -9.1409
Max Act: 9.0159. Min Act: -0.1700
Data Index: 7848948 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.8909. Min Act: -0.1700
Data Index: 3921622 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.7659. Min Act: -0.1700
Data Index: 7848949 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.8284. Min Act: -0.1700
Data Index: 8116022 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.8284. Min Act: -0.1700
Data Index: 4438458 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.7659. Min Act: -0.1700
Data Index: 799328 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.7659. Min Act: -0.1700
Data Index: 3996484 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.7034. Min Act: -0.1700
Data Index: 6826182 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.6409. Min Act: -0.1700
Data Index: 1750623 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.6409. Min Act: -0.1700
Data Index: 4473423 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.5784. Min Act: -0.1700
Data Index: 7211618 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.6409. Min Act: -0.1700
Data Index: 5918630 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.5784. Min Act: -0.1700
Data Index: 2081473 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.5784. Min Act: -0.1700
Data Index: 7126829 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.5159. Min Act: -0.1700
Data Index: 2129252 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.5159. Min Act: -0.1700
Data Index: 3920979 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.4534. Min Act: -0.1700
Data Index: 1109377 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1409. Min Range: -9.1409
Max Act: 8.5159. Min Act: -0.1700
Data Index: 5867747 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19