Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 509 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1373. Min Range: -5.1373
Max Act: 5.1373. Min Act: -0.1700
Data Index: 1873986 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1373. Min Range: -5.1373
Max Act: 5.0123. Min Act: -0.1700
Data Index: 5531775 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1373. Min Range: -5.1373
Max Act: 5.0748. Min Act: -0.1700
Data Index: 5825260 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1373. Min Range: -5.1373
Max Act: 5.0123. Min Act: -0.1700
Data Index: 5336914 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1373. Min Range: -5.1373
Max Act: 5.0123. Min Act: -0.1700
Data Index: 8297969 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9810. Min Act: -0.1700
Data Index: 8615114 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1373. Min Range: -5.1373
Max Act: 5.0123. Min Act: -0.1700
Data Index: 995702 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9810. Min Act: -0.1700
Data Index: 5238897 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9810. Min Act: -0.1700
Data Index: 2196655 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9498. Min Act: -0.1700
Data Index: 4778984 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9498. Min Act: -0.1700
Data Index: 247031 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9810. Min Act: -0.1700
Data Index: 4516764 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9810. Min Act: -0.1700
Data Index: 49099 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9498. Min Act: -0.1700
Data Index: 6412991 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9498. Min Act: -0.1700
Data Index: 8671438 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9185. Min Act: -0.1700
Data Index: 505034 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9185. Min Act: -0.1700
Data Index: 2715647 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9185. Min Act: -0.1700
Data Index: 4982086 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9185. Min Act: -0.1700
Data Index: 5131674 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1373. Min Range: -5.1373
Max Act: 4.9185. Min Act: -0.1700
Data Index: 2084037 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19