Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.9583. Min Act: -0.1700
Data Index: 8828447 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.8645. Min Act: -0.1700
Data Index: 6196330 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.8645. Min Act: -0.1700
Data Index: 2555849 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.8645. Min Act: -0.1700
Data Index: 8373899 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.8332. Min Act: -0.1700
Data Index: 2515998 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.8332. Min Act: -0.1700
Data Index: 7730546 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.8332. Min Act: -0.1700
Data Index: 8805242 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.8020. Min Act: -0.1700
Data Index: 8564462 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.7707. Min Act: -0.1700
Data Index: 8472302 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.7707. Min Act: -0.1700
Data Index: 6257874 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.7394. Min Act: -0.1700
Data Index: 4324438 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.7394. Min Act: -0.1700
Data Index: 3366833 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.7394. Min Act: -0.1700
Data Index: 4055990 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.7081. Min Act: -0.1700
Data Index: 1218904 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.7081. Min Act: -0.1700
Data Index: 6459388 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.7081. Min Act: -0.1700
Data Index: 3340883 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.7081. Min Act: -0.1700
Data Index: 728126 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.6768. Min Act: -0.1700
Data Index: 7057230 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.6768. Min Act: -0.1700
Data Index: 7943080 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9583. Min Range: -3.9583
Max Act: 3.6768. Min Act: -0.1700
Data Index: 894389 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19