Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1826. Min Range: -2.1826
Max Act: 2.1826. Min Act: -0.1700
Data Index: 5756695 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1826. Min Range: -2.1826
Max Act: 2.1327. Min Act: -0.1700
Data Index: 8568585 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1826. Min Range: -2.1826
Max Act: 2.0489. Min Act: -0.1700
Data Index: 7244966 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1826. Min Range: -2.1826
Max Act: 2.0657. Min Act: -0.1700
Data Index: 2353577 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1826. Min Range: -2.1826
Max Act: 2.0489. Min Act: -0.1700
Data Index: 1387907 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1826. Min Range: -2.1826
Max Act: 2.0320. Min Act: -0.1700
Data Index: 455038 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1826. Min Range: -2.1826
Max Act: 2.0320. Min Act: -0.1700
Data Index: 2250505 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1826. Min Range: -2.1826
Max Act: 2.0320. Min Act: -0.1700
Data Index: 1268948 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9983. Min Act: -0.1700
Data Index: 7740142 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9983. Min Act: -0.1700
Data Index: 4790889 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9983. Min Act: -0.1700
Data Index: 1520002 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9983. Min Act: -0.1700
Data Index: 4820661 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9814. Min Act: -0.1700
Data Index: 3711196 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9983. Min Act: -0.1700
Data Index: 2720230 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9474. Min Act: -0.1700
Data Index: 1782273 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9644. Min Act: -0.1700
Data Index: 257309 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9644. Min Act: -0.1700
Data Index: 6620789 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9644. Min Act: -0.1700
Data Index: 3113171 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9474. Min Act: -0.1700
Data Index: 6763628 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1826. Min Range: -2.1826
Max Act: 1.9474. Min Act: -0.1700
Data Index: 4885369 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19