Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1299 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0053. Min Range: -3.0053
Max Act: 3.0053. Min Act: -0.1700
Data Index: 1028696 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.9894. Min Act: -0.1700
Data Index: 8191366 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.9578. Min Act: -0.1700
Data Index: 4614155 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.9103. Min Act: -0.1700
Data Index: 5971334 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8786. Min Act: -0.1700
Data Index: 8550298 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8786. Min Act: -0.1700
Data Index: 6422275 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8786. Min Act: -0.1700
Data Index: 82116 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8786. Min Act: -0.1700
Data Index: 169220 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8627. Min Act: -0.1700
Data Index: 1040334 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8627. Min Act: -0.1700
Data Index: 8270493 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8468. Min Act: -0.1700
Data Index: 5914475 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8627. Min Act: -0.1700
Data Index: 2910 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8309. Min Act: -0.1700
Data Index: 5074599 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8468. Min Act: -0.1700
Data Index: 4704386 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8468. Min Act: -0.1700
Data Index: 6754188 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8468. Min Act: -0.1700
Data Index: 3247952 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8627. Min Act: -0.1700
Data Index: 6265623 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8309. Min Act: -0.1700
Data Index: 5884571 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8309. Min Act: -0.1700
Data Index: 4330906 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0053. Min Range: -3.0053
Max Act: 2.8309. Min Act: -0.1700
Data Index: 621981 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19