Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3616 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.9068. Min Act: -0.1700
Data Index: 5931157 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.3443. Min Act: -0.1700
Data Index: 3795732 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.3756. Min Act: -0.1700
Data Index: 8452473 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.3756. Min Act: -0.1700
Data Index: 4266725 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.3756. Min Act: -0.1700
Data Index: 6227505 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.2818. Min Act: -0.1700
Data Index: 7846471 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.2193. Min Act: -0.1700
Data Index: 3353516 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.2506. Min Act: -0.1700
Data Index: 6415645 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.2193. Min Act: -0.1700
Data Index: 814926 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1881. Min Act: -0.1700
Data Index: 1431999 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1881. Min Act: -0.1700
Data Index: 7908917 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1881. Min Act: -0.1700
Data Index: 7667577 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1568. Min Act: -0.1700
Data Index: 4797331 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1568. Min Act: -0.1700
Data Index: 5731068 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1568. Min Act: -0.1700
Data Index: 898864 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1568. Min Act: -0.1700
Data Index: 6198139 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1881. Min Act: -0.1700
Data Index: 1874847 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1256. Min Act: -0.1700
Data Index: 7031422 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1256. Min Act: -0.1700
Data Index: 1345101 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9068. Min Range: -7.9068
Max Act: 7.1256. Min Act: -0.1700
Data Index: 7021272 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19