Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5077 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0008. Min Range: -11.0008
Max Act: 11.0008. Min Act: -0.1700
Data Index: 8098237 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0008. Min Range: -11.0008
Max Act: 10.6883. Min Act: -0.1700
Data Index: 1584432 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0008. Min Range: -11.0008
Max Act: 10.1883. Min Act: -0.1700
Data Index: 2176285 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0008. Min Range: -11.0008
Max Act: 10.0633. Min Act: -0.1700
Data Index: 3907981 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0008. Min Range: -11.0008
Max Act: 10.0008. Min Act: -0.1700
Data Index: 2585783 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0008. Min Range: -11.0008
Max Act: 10.0008. Min Act: -0.1700
Data Index: 8392538 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.9383. Min Act: -0.1700
Data Index: 3633712 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.7508. Min Act: -0.1700
Data Index: 6489882 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.6883. Min Act: -0.1700
Data Index: 5111867 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.6258. Min Act: -0.1700
Data Index: 7381885 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.5008. Min Act: -0.1700
Data Index: 4483631 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.5633. Min Act: -0.1700
Data Index: 569122 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.6258. Min Act: -0.1700
Data Index: 5937735 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.6258. Min Act: -0.1700
Data Index: 3455422 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.5633. Min Act: -0.1700
Data Index: 7001441 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.5633. Min Act: -0.1700
Data Index: 3804910 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.5008. Min Act: -0.1700
Data Index: 3705122 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.5633. Min Act: -0.1700
Data Index: 7121698 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.5008. Min Act: -0.1700
Data Index: 20277 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0008. Min Range: -11.0008
Max Act: 9.5633. Min Act: -0.1700
Data Index: 4817524 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19