Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3688 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.7410. Min Act: -0.1700
Data Index: 8473994 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.2097. Min Act: -0.1700
Data Index: 6986367 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.1785. Min Act: -0.1700
Data Index: 4610549 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.1785. Min Act: -0.1700
Data Index: 1682206 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.1785. Min Act: -0.1700
Data Index: 3643143 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.0847. Min Act: -0.1700
Data Index: 3672376 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.0535. Min Act: -0.1700
Data Index: 1705173 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.9285. Min Act: -0.1700
Data Index: 8160145 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.9285. Min Act: -0.1700
Data Index: 8705215 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.9285. Min Act: -0.1700
Data Index: 1837177 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.9285. Min Act: -0.1700
Data Index: 378179 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.9285. Min Act: -0.1700
Data Index: 1765591 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.8972. Min Act: -0.1700
Data Index: 8208963 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.8972. Min Act: -0.1700
Data Index: 8809068 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.8972. Min Act: -0.1700
Data Index: 7771043 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.8972. Min Act: -0.1700
Data Index: 4716974 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.8972. Min Act: -0.1700
Data Index: 7639524 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.8660. Min Act: -0.1700
Data Index: 3350236 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.8660. Min Act: -0.1700
Data Index: 1222124 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7410. Min Range: -5.7410
Max Act: 4.8660. Min Act: -0.1700
Data Index: 1749600 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19