Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.9924. Min Act: -0.1700
Data Index: 3628523 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.9299. Min Act: -0.1700
Data Index: 2652854 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8986. Min Act: -0.1700
Data Index: 8251882 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8986. Min Act: -0.1700
Data Index: 5035507 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8674. Min Act: -0.1700
Data Index: 5088623 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8986. Min Act: -0.1700
Data Index: 657186 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8674. Min Act: -0.1700
Data Index: 1456576 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8361. Min Act: -0.1700
Data Index: 303859 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8048. Min Act: -0.1700
Data Index: 726184 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8361. Min Act: -0.1700
Data Index: 5492292 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8361. Min Act: -0.1700
Data Index: 462661 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8048. Min Act: -0.1700
Data Index: 3789910 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8048. Min Act: -0.1700
Data Index: 929889 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.8361. Min Act: -0.1700
Data Index: 5621286 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.7736. Min Act: -0.1700
Data Index: 5723470 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.7736. Min Act: -0.1700
Data Index: 5875778 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.6954. Min Act: -0.1700
Data Index: 5123299 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.7736. Min Act: -0.1700
Data Index: 6623939 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.7736. Min Act: -0.1700
Data Index: 1775087 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9924. Min Range: -3.9924
Max Act: 3.7266. Min Act: -0.1700
Data Index: 4147157 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19