Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5776 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.6787. Min Act: -0.1700
Data Index: 5996184 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.4287. Min Act: -0.1700
Data Index: 5432784 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.4287. Min Act: -0.1700
Data Index: 8081560 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.3662. Min Act: -0.1700
Data Index: 3408551 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.2412. Min Act: -0.1700
Data Index: 5746050 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.2412. Min Act: -0.1700
Data Index: 8466334 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.1787. Min Act: -0.1700
Data Index: 1734237 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.1787. Min Act: -0.1700
Data Index: 2337017 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.1474. Min Act: -0.1700
Data Index: 3786573 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.1474. Min Act: -0.1700
Data Index: 1293543 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.1474. Min Act: -0.1700
Data Index: 4819355 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.0849. Min Act: -0.1700
Data Index: 5600664 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.1162. Min Act: -0.1700
Data Index: 7903553 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.1162. Min Act: -0.1700
Data Index: 2036753 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.0537. Min Act: -0.1700
Data Index: 1377832 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.0537. Min Act: -0.1700
Data Index: 8045282 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6787. Min Range: -6.6787
Max Act: 6.0224. Min Act: -0.1700
Data Index: 327343 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6787. Min Range: -6.6787
Max Act: 5.9599. Min Act: -0.1700
Data Index: 7413619 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6787. Min Range: -6.6787
Max Act: 5.9912. Min Act: -0.1700
Data Index: 449661 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6787. Min Range: -6.6787
Max Act: 5.9912. Min Act: -0.1700
Data Index: 65160 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19