Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4763 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1780. Min Range: -8.1780
Max Act: 8.1780. Min Act: -0.1700
Data Index: 4484911 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.9280. Min Act: -0.1700
Data Index: 2804626 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.6780. Min Act: -0.1700
Data Index: 401992 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.5530. Min Act: -0.1700
Data Index: 1751533 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.5530. Min Act: -0.1700
Data Index: 4471743 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.4592. Min Act: -0.1700
Data Index: 450152 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.4280. Min Act: -0.1700
Data Index: 5004737 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.4280. Min Act: -0.1700
Data Index: 79810 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.4280. Min Act: -0.1700
Data Index: 108797 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.3967. Min Act: -0.1700
Data Index: 939093 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.3967. Min Act: -0.1700
Data Index: 5436563 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.3655. Min Act: -0.1700
Data Index: 8830501 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.3655. Min Act: -0.1700
Data Index: 5940705 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.3342. Min Act: -0.1700
Data Index: 5229498 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.3342. Min Act: -0.1700
Data Index: 4447232 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.2717. Min Act: -0.1700
Data Index: 6666094 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.2717. Min Act: -0.1700
Data Index: 1241808 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.2717. Min Act: -0.1700
Data Index: 1889703 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.2405. Min Act: -0.1700
Data Index: 2017466 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1780. Min Range: -8.1780
Max Act: 7.2092. Min Act: -0.1700
Data Index: 4731487 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19