Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.4104. Min Act: -0.1700
Data Index: 6935821 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.4104. Min Act: -0.1700
Data Index: 552033 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.2542. Min Act: -0.1700
Data Index: 1646699 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.2229. Min Act: -0.1700
Data Index: 5665376 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.2229. Min Act: -0.1700
Data Index: 6870085 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.1604. Min Act: -0.1700
Data Index: 3430521 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.1604. Min Act: -0.1700
Data Index: 5694952 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.1604. Min Act: -0.1700
Data Index: 5694282 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.1292. Min Act: -0.1700
Data Index: 6894417 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.0979. Min Act: -0.1700
Data Index: 3093142 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.0979. Min Act: -0.1700
Data Index: 1968490 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.0979. Min Act: -0.1700
Data Index: 3382792 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.0667. Min Act: -0.1700
Data Index: 7102789 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.0667. Min Act: -0.1700
Data Index: 3335182 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.0354. Min Act: -0.1700
Data Index: 2620339 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.0667. Min Act: -0.1700
Data Index: 2386850 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4104. Min Range: -6.4104
Max Act: 6.0042. Min Act: -0.1700
Data Index: 5104670 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4104. Min Range: -6.4104
Max Act: 5.9729. Min Act: -0.1700
Data Index: 6207989 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4104. Min Range: -6.4104
Max Act: 5.9729. Min Act: -0.1700
Data Index: 4350431 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4104. Min Range: -6.4104
Max Act: 5.9729. Min Act: -0.1700
Data Index: 3039005 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19