Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.8808. Min Act: -0.1700
Data Index: 5994084 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.8496. Min Act: -0.1700
Data Index: 5994081 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.8496. Min Act: -0.1700
Data Index: 5994085 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.8183. Min Act: -0.1700
Data Index: 5994083 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.7870. Min Act: -0.1700
Data Index: 3866632 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.7870. Min Act: -0.1700
Data Index: 3510798 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.7558. Min Act: -0.1700
Data Index: 5994086 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.7245. Min Act: -0.1700
Data Index: 510010 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.7245. Min Act: -0.1700
Data Index: 4550100 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.7245. Min Act: -0.1700
Data Index: 7799100 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.7245. Min Act: -0.1700
Data Index: 6306041 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.6933. Min Act: -0.1700
Data Index: 5994079 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.6933. Min Act: -0.1700
Data Index: 4667314 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.6933. Min Act: -0.1700
Data Index: 5205397 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.6933. Min Act: -0.1700
Data Index: 1377232 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.6933. Min Act: -0.1700
Data Index: 1502109 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.6933. Min Act: -0.1700
Data Index: 2991535 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.6933. Min Act: -0.1700
Data Index: 3866635 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.6933. Min Act: -0.1700
Data Index: 4859671 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8808. Min Range: -4.8808
Max Act: 4.6933. Min Act: -0.1700
Data Index: 6127723 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19