Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.8308. Min Act: -0.1700
Data Index: 8808086 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.8308. Min Act: -0.1700
Data Index: 7783344 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.7058. Min Act: -0.1700
Data Index: 8030144 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6745. Min Act: -0.1700
Data Index: 5975343 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6433. Min Act: -0.1700
Data Index: 606206 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6433. Min Act: -0.1700
Data Index: 8180070 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6433. Min Act: -0.1700
Data Index: 7367306 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6433. Min Act: -0.1700
Data Index: 5926786 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6433. Min Act: -0.1700
Data Index: 2977844 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6433. Min Act: -0.1700
Data Index: 4587434 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.5808. Min Act: -0.1700
Data Index: 7759335 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6120. Min Act: -0.1700
Data Index: 4043789 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6120. Min Act: -0.1700
Data Index: 7280444 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.6120. Min Act: -0.1700
Data Index: 7852895 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.5808. Min Act: -0.1700
Data Index: 868774 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.5808. Min Act: -0.1700
Data Index: 3482797 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.5808. Min Act: -0.1700
Data Index: 5842417 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.5495. Min Act: -0.1700
Data Index: 5619180 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.5495. Min Act: -0.1700
Data Index: 1443427 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8308. Min Range: -4.8308
Max Act: 4.5183. Min Act: -0.1700
Data Index: 1486020 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19