Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.8666. Min Act: -0.1700
Data Index: 2703186 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.5229. Min Act: -0.1700
Data Index: 7613810 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.4916. Min Act: -0.1700
Data Index: 2845437 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.4291. Min Act: -0.1700
Data Index: 4901887 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.3979. Min Act: -0.1700
Data Index: 1979349 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.4291. Min Act: -0.1700
Data Index: 155785 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.3354. Min Act: -0.1700
Data Index: 155786 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.3041. Min Act: -0.1700
Data Index: 2136893 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.2104. Min Act: -0.1700
Data Index: 5193170 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1791. Min Act: -0.1700
Data Index: 5635432 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1791. Min Act: -0.1700
Data Index: 558556 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1479. Min Act: -0.1700
Data Index: 4282554 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1479. Min Act: -0.1700
Data Index: 3254193 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1479. Min Act: -0.1700
Data Index: 2733849 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1791. Min Act: -0.1700
Data Index: 8264696 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1479. Min Act: -0.1700
Data Index: 929579 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1166. Min Act: -0.1700
Data Index: 6187013 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1166. Min Act: -0.1700
Data Index: 3307518 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.1479. Min Act: -0.1700
Data Index: 6921559 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8666. Min Range: -6.8666
Max Act: 6.0854. Min Act: -0.1700
Data Index: 1241495 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19