Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3402 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1797. Min Range: -4.1797
Max Act: 4.1797. Min Act: -0.1700
Data Index: 7736292 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1797. Min Range: -4.1797
Max Act: 4.0859. Min Act: -0.1700
Data Index: 4597231 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1797. Min Range: -4.1797
Max Act: 4.0859. Min Act: -0.1700
Data Index: 2164708 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1797. Min Range: -4.1797
Max Act: 4.0547. Min Act: -0.1700
Data Index: 5295324 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1797. Min Range: -4.1797
Max Act: 4.0547. Min Act: -0.1700
Data Index: 6435674 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1797. Min Range: -4.1797
Max Act: 4.0234. Min Act: -0.1700
Data Index: 4205270 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.9922. Min Act: -0.1700
Data Index: 8671961 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.9296. Min Act: -0.1700
Data Index: 79707 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.8984. Min Act: -0.1700
Data Index: 3744713 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.8358. Min Act: -0.1700
Data Index: 4933217 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.8671. Min Act: -0.1700
Data Index: 4606058 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.8671. Min Act: -0.1700
Data Index: 5200723 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.8358. Min Act: -0.1700
Data Index: 1788954 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.8046. Min Act: -0.1700
Data Index: 7227192 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.8358. Min Act: -0.1700
Data Index: 139837 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.8046. Min Act: -0.1700
Data Index: 4788905 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.7733. Min Act: -0.1700
Data Index: 2409421 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.7733. Min Act: -0.1700
Data Index: 5489620 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.7733. Min Act: -0.1700
Data Index: 391970 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1797. Min Range: -4.1797
Max Act: 3.7420. Min Act: -0.1700
Data Index: 4360777 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19