Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 164 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1475. Min Range: -6.1475
Max Act: 6.1162. Min Act: -0.1700
Data Index: 8458630 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1475. Min Range: -6.1475
Max Act: 6.1475. Min Act: -0.1700
Data Index: 3735853 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.9600. Min Act: -0.1700
Data Index: 1071206 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.9600. Min Act: -0.1700
Data Index: 7819359 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.8662. Min Act: -0.1700
Data Index: 4794122 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.8037. Min Act: -0.1700
Data Index: 5860682 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.7725. Min Act: -0.1700
Data Index: 5982646 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.7725. Min Act: -0.1700
Data Index: 5065703 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.7725. Min Act: -0.1700
Data Index: 7004467 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.6787. Min Act: -0.1697
Data Index: 1861416 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.6787. Min Act: -0.1700
Data Index: 6113340 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.5850. Min Act: -0.1700
Data Index: 5562771 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.6475. Min Act: -0.1700
Data Index: 3392468 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.6475. Min Act: -0.1700
Data Index: 4754462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.5850. Min Act: -0.1699
Data Index: 1421124 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.6162. Min Act: -0.1700
Data Index: 2623589 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.5850. Min Act: -0.1700
Data Index: 2455927 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.5850. Min Act: -0.1700
Data Index: 1994705 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.5537. Min Act: -0.1700
Data Index: 6268452 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1475. Min Range: -6.1475
Max Act: 5.5850. Min Act: -0.1699
Data Index: 4863200 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19