Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 472 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.1826. Min Act: -0.1700
Data Index: 6214557 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.1826. Min Act: -0.1700
Data Index: 1630320 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.1201. Min Act: -0.1700
Data Index: 7259354 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.1201. Min Act: -0.1700
Data Index: 1898084 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.1201. Min Act: -0.1700
Data Index: 3828823 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.1513. Min Act: -0.1700
Data Index: 1606777 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.0576. Min Act: -0.1700
Data Index: 8780390 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.1201. Min Act: -0.1700
Data Index: 6413684 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.0888. Min Act: -0.1700
Data Index: 501566 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.0888. Min Act: -0.1700
Data Index: 3185639 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1826. Min Range: -6.1826
Max Act: 6.0576. Min Act: -0.1700
Data Index: 5937579 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1826. Min Range: -6.1826
Max Act: 5.9638. Min Act: -0.1700
Data Index: 1457895 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1826. Min Range: -6.1826
Max Act: 5.9951. Min Act: -0.1700
Data Index: 3661190 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1826. Min Range: -6.1826
Max Act: 5.9951. Min Act: -0.1700
Data Index: 3192152 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1826. Min Range: -6.1826
Max Act: 5.9951. Min Act: -0.1700
Data Index: 3884399 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1826. Min Range: -6.1826
Max Act: 5.9638. Min Act: -0.1700
Data Index: 4840539 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1826. Min Range: -6.1826
Max Act: 5.9638. Min Act: -0.1700
Data Index: 6982616 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1826. Min Range: -6.1826
Max Act: 5.9951. Min Act: -0.1700
Data Index: 7218049 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1826. Min Range: -6.1826
Max Act: 5.9951. Min Act: -0.1700
Data Index: 5895306 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1826. Min Range: -6.1826
Max Act: 5.9638. Min Act: -0.1700
Data Index: 6175797 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19