Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4549 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.2343. Min Act: -0.1700
Data Index: 5326075 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.2655. Min Act: -0.1700
Data Index: 5646057 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.2655. Min Act: -0.1700
Data Index: 6662402 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.2030. Min Act: -0.1700
Data Index: 6327013 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.1718. Min Act: -0.1700
Data Index: 1438687 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.1405. Min Act: -0.1700
Data Index: 6662407 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.1405. Min Act: -0.1700
Data Index: 753188 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.1093. Min Act: -0.1700
Data Index: 3256742 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.0780. Min Act: -0.1700
Data Index: 556248 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.0780. Min Act: -0.1700
Data Index: 6172928 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.0780. Min Act: -0.1700
Data Index: 5216958 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2655. Min Range: -7.2655
Max Act: 7.0468. Min Act: -0.1700
Data Index: 2111993 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2655. Min Range: -7.2655
Max Act: 6.9843. Min Act: -0.1700
Data Index: 3120363 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2655. Min Range: -7.2655
Max Act: 6.9530. Min Act: -0.1700
Data Index: 2202421 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2655. Min Range: -7.2655
Max Act: 6.9218. Min Act: -0.1700
Data Index: 5666544 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2655. Min Range: -7.2655
Max Act: 6.9530. Min Act: -0.1700
Data Index: 8678367 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2655. Min Range: -7.2655
Max Act: 6.9530. Min Act: -0.1700
Data Index: 5618116 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2655. Min Range: -7.2655
Max Act: 6.8905. Min Act: -0.1700
Data Index: 5771272 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2655. Min Range: -7.2655
Max Act: 6.8593. Min Act: -0.1700
Data Index: 4144626 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2655. Min Range: -7.2655
Max Act: 6.8593. Min Act: -0.1700
Data Index: 8612004 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19