Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2242 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8996. Min Range: -12.8996
Max Act: 12.8996. Min Act: -0.1700
Data Index: 5914103 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8996. Min Range: -12.8996
Max Act: 12.5246. Min Act: -0.1700
Data Index: 67137 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8996. Min Range: -12.8996
Max Act: 12.3996. Min Act: -0.1700
Data Index: 5085741 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8996. Min Range: -12.8996
Max Act: 12.3371. Min Act: -0.1700
Data Index: 8240036 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8996. Min Range: -12.8996
Max Act: 12.0246. Min Act: -0.1700
Data Index: 7232133 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8996. Min Range: -12.8996
Max Act: 12.0246. Min Act: -0.1700
Data Index: 3664168 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.8371. Min Act: -0.1700
Data Index: 8226963 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.8371. Min Act: -0.1700
Data Index: 3573248 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.8371. Min Act: -0.1700
Data Index: 4187456 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.6496. Min Act: -0.1700
Data Index: 7600807 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.5871. Min Act: -0.1700
Data Index: 3977844 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.5871. Min Act: -0.1700
Data Index: 5556235 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.5871. Min Act: -0.1700
Data Index: 2959565 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.5246. Min Act: -0.1700
Data Index: 5598545 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.4621. Min Act: -0.1700
Data Index: 1447340 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.3371. Min Act: -0.1700
Data Index: 1426132 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.3996. Min Act: -0.1700
Data Index: 5499652 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.3996. Min Act: -0.1700
Data Index: 6615486 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.3996. Min Act: -0.1700
Data Index: 4857197 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8996. Min Range: -12.8996
Max Act: 11.2746. Min Act: -0.1700
Data Index: 5059820 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19