Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.9269. Min Act: -0.1700
Data Index: 7605251 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8928. Min Act: -0.1700
Data Index: 359826 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.9014. Min Act: -0.1700
Data Index: 6757379 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8928. Min Act: -0.1700
Data Index: 4898040 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8843. Min Act: -0.1700
Data Index: 1432496 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8928. Min Act: -0.1700
Data Index: 1380316 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8758. Min Act: -0.1700
Data Index: 6817753 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8758. Min Act: -0.1700
Data Index: 4212535 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8843. Min Act: -0.1700
Data Index: 1220055 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8672. Min Act: -0.1662
Data Index: 4560805 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8758. Min Act: -0.1700
Data Index: 7457406 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8758. Min Act: -0.1700
Data Index: 3412208 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8758. Min Act: -0.1700
Data Index: 7957856 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8672. Min Act: -0.1700
Data Index: 7443740 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8587. Min Act: -0.1700
Data Index: 4280368 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8501. Min Act: -0.1699
Data Index: 669838 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8587. Min Act: -0.1700
Data Index: 5784352 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8415. Min Act: -0.1698
Data Index: 2955097 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8501. Min Act: -0.1700
Data Index: 6809675 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9269. Min Range: -1.9269
Max Act: 1.8415. Min Act: -0.1700
Data Index: 6950845 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19