Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1604. Min Range: -7.1604
Max Act: 7.1604. Min Act: -0.1700
Data Index: 6989488 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.9416. Min Act: -0.1700
Data Index: 5038426 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.9104. Min Act: -0.1700
Data Index: 2180582 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.8479. Min Act: -0.1700
Data Index: 5038425 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.8479. Min Act: -0.1700
Data Index: 2180584 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.8166. Min Act: -0.1700
Data Index: 1166779 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.6916. Min Act: -0.1700
Data Index: 699068 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.6916. Min Act: -0.1700
Data Index: 5989714 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.5666. Min Act: -0.1700
Data Index: 3736757 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.5354. Min Act: -0.1700
Data Index: 21143 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.5041. Min Act: -0.1700
Data Index: 1815276 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.4729. Min Act: -0.1700
Data Index: 5998176 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.4729. Min Act: -0.1700
Data Index: 4217239 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.4416. Min Act: -0.1700
Data Index: 949276 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.4729. Min Act: -0.1700
Data Index: 2940788 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.3791. Min Act: -0.1700
Data Index: 1007417 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.4104. Min Act: -0.1700
Data Index: 3795787 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.3791. Min Act: -0.1700
Data Index: 4645162 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.3166. Min Act: -0.1700
Data Index: 6474614 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1604. Min Range: -7.1604
Max Act: 6.3479. Min Act: -0.1700
Data Index: 1158897 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19