Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1453 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.2141. Min Act: -0.1700
Data Index: 2012861 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.2453. Min Act: -0.1700
Data Index: 6015090 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.2141. Min Act: -0.1700
Data Index: 8597938 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1828. Min Act: -0.1700
Data Index: 2117116 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1828. Min Act: -0.1700
Data Index: 6786795 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1516. Min Act: -0.1700
Data Index: 3632352 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1516. Min Act: -0.1700
Data Index: 732630 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1203. Min Act: -0.1700
Data Index: 6391786 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1516. Min Act: -0.1700
Data Index: 3541838 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1203. Min Act: -0.1700
Data Index: 4945000 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1516. Min Act: -0.1700
Data Index: 743889 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1203. Min Act: -0.1700
Data Index: 151114 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1203. Min Act: -0.1700
Data Index: 8813691 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0891. Min Act: -0.1700
Data Index: 6685661 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0891. Min Act: -0.1700
Data Index: 6155843 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0578. Min Act: -0.1700
Data Index: 4057840 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1203. Min Act: -0.1700
Data Index: 1110912 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0891. Min Act: -0.1700
Data Index: 6184907 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0578. Min Act: -0.1700
Data Index: 4572040 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0578. Min Act: -0.1700
Data Index: 3632354 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19