Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4220 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0410. Min Range: -6.0410
Max Act: 6.0410. Min Act: -0.1700
Data Index: 7863477 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.9473. Min Act: -0.1700
Data Index: 5708271 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.8535. Min Act: -0.1700
Data Index: 4077589 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.8535. Min Act: -0.1700
Data Index: 550324 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.8535. Min Act: -0.1700
Data Index: 673009 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.8223. Min Act: -0.1700
Data Index: 5455454 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.7910. Min Act: -0.1700
Data Index: 1023850 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.7910. Min Act: -0.1700
Data Index: 8805633 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.7285. Min Act: -0.1700
Data Index: 4006051 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6973. Min Act: -0.1700
Data Index: 6562152 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6973. Min Act: -0.1700
Data Index: 6122095 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.7285. Min Act: -0.1700
Data Index: 1023034 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6973. Min Act: -0.1699
Data Index: 6028328 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6660. Min Act: -0.1700
Data Index: 5937706 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6973. Min Act: -0.1700
Data Index: 2631581 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6973. Min Act: -0.1699
Data Index: 5451808 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6973. Min Act: -0.1700
Data Index: 5111507 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6973. Min Act: -0.1700
Data Index: 3599241 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6660. Min Act: -0.1700
Data Index: 2325012 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0410. Min Range: -6.0410
Max Act: 5.6973. Min Act: -0.1700
Data Index: 7769619 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19