Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.1663. Min Act: -0.1700
Data Index: 5385684 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.1350. Min Act: -0.1700
Data Index: 6230250 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0725. Min Act: -0.1700
Data Index: 8378672 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0725. Min Act: -0.1700
Data Index: 7110507 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0100. Min Act: -0.1700
Data Index: 4350767 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9475. Min Act: -0.1700
Data Index: 262187 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9475. Min Act: -0.1700
Data Index: 1884778 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9475. Min Act: -0.1700
Data Index: 8011555 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9475. Min Act: -0.1700
Data Index: 8397190 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9788. Min Act: -0.1700
Data Index: 4171900 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 3718755 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 511043 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 2310893 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 6735265 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8538. Min Act: -0.1700
Data Index: 6230249 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 5613102 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 4889862 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 8223632 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8538. Min Act: -0.1700
Data Index: 5500177 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8538. Min Act: -0.1700
Data Index: 1798573 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19