Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2207 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5361. Min Range: -8.5361
Max Act: 8.5361. Min Act: -0.1700
Data Index: 4828723 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5361. Min Range: -8.5361
Max Act: 8.4736. Min Act: -0.1700
Data Index: 601226 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5361. Min Range: -8.5361
Max Act: 8.1611. Min Act: -0.1700
Data Index: 8076576 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5361. Min Range: -8.5361
Max Act: 8.0986. Min Act: -0.1700
Data Index: 3691840 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5361. Min Range: -8.5361
Max Act: 8.0361. Min Act: -0.1700
Data Index: 5930721 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5361. Min Range: -8.5361
Max Act: 8.0986. Min Act: -0.1700
Data Index: 8012708 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5361. Min Range: -8.5361
Max Act: 8.0361. Min Act: -0.1700
Data Index: 6405764 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.9736. Min Act: -0.1700
Data Index: 972059 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.9111. Min Act: -0.1700
Data Index: 8429380 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.9111. Min Act: -0.1700
Data Index: 2524528 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.9111. Min Act: -0.1700
Data Index: 661616 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.9111. Min Act: -0.1700
Data Index: 5708499 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.9111. Min Act: -0.1700
Data Index: 3560818 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.9111. Min Act: -0.1700
Data Index: 2447162 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.9111. Min Act: -0.1700
Data Index: 4715279 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.8486. Min Act: -0.1700
Data Index: 496966 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.8486. Min Act: -0.1700
Data Index: 7031846 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.8486. Min Act: -0.1700
Data Index: 4391313 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.8486. Min Act: -0.1700
Data Index: 5725509 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5361. Min Range: -8.5361
Max Act: 7.8486. Min Act: -0.1700
Data Index: 168060 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19