Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5432 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0537. Min Range: -8.0537
Max Act: 8.0537. Min Act: -0.1700
Data Index: 5341031 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0537. Min Range: -8.0537
Max Act: 8.0537. Min Act: -0.1700
Data Index: 4766386 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.9912. Min Act: -0.1700
Data Index: 4969619 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.9287. Min Act: -0.1700
Data Index: 8394482 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.9287. Min Act: -0.1700
Data Index: 2938407 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.8662. Min Act: -0.1700
Data Index: 8805494 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.8662. Min Act: -0.1700
Data Index: 2479174 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.8662. Min Act: -0.1700
Data Index: 4479775 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.8037. Min Act: -0.1700
Data Index: 101855 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.8037. Min Act: -0.1700
Data Index: 829172 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.7412. Min Act: -0.1700
Data Index: 6953160 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.7412. Min Act: -0.1700
Data Index: 8056769 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.7412. Min Act: -0.1700
Data Index: 8042338 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.6787. Min Act: -0.1700
Data Index: 249585 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.6787. Min Act: -0.1700
Data Index: 100269 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.6787. Min Act: -0.1700
Data Index: 2543267 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.6787. Min Act: -0.1700
Data Index: 739063 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.6787. Min Act: -0.1700
Data Index: 7760363 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.6787. Min Act: -0.1700
Data Index: 4004729 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0537. Min Range: -8.0537
Max Act: 7.6787. Min Act: -0.1700
Data Index: 7655188 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19