Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0659. Min Range: -10.0659
Max Act: 10.0659. Min Act: -0.1700
Data Index: 3471686 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.4409. Min Act: -0.1700
Data Index: 7428538 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.3784. Min Act: -0.1700
Data Index: 5105071 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.3784. Min Act: -0.1700
Data Index: 8535771 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.3784. Min Act: -0.1700
Data Index: 4776705 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.3784. Min Act: -0.1700
Data Index: 7928943 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.2534. Min Act: -0.1700
Data Index: 5267759 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.0659. Min Act: -0.1700
Data Index: 4244228 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.0659. Min Act: -0.1700
Data Index: 5408845 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.0034. Min Act: -0.1700
Data Index: 5767080 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.0034. Min Act: -0.1700
Data Index: 4878543 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.0034. Min Act: -0.1700
Data Index: 3985459 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0659. Min Range: -10.0659
Max Act: 8.9409. Min Act: -0.1700
Data Index: 4914167 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0659. Min Range: -10.0659
Max Act: 9.0034. Min Act: -0.1700
Data Index: 5530437 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0659. Min Range: -10.0659
Max Act: 8.8784. Min Act: -0.1700
Data Index: 8729244 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0659. Min Range: -10.0659
Max Act: 8.9409. Min Act: -0.1700
Data Index: 8541659 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0659. Min Range: -10.0659
Max Act: 8.8784. Min Act: -0.1700
Data Index: 5778306 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0659. Min Range: -10.0659
Max Act: 8.8784. Min Act: -0.1700
Data Index: 4303593 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0659. Min Range: -10.0659
Max Act: 8.8784. Min Act: -0.1700
Data Index: 920885 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0659. Min Range: -10.0659
Max Act: 8.8784. Min Act: -0.1700
Data Index: 505060 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19