Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.6660. Min Act: -0.1700
Data Index: 3490857 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.2598. Min Act: -0.1700
Data Index: 4325337 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.2285. Min Act: -0.1700
Data Index: 3087709 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.2285. Min Act: -0.1700
Data Index: 1023707 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.1973. Min Act: -0.1700
Data Index: 5990895 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.1348. Min Act: -0.1700
Data Index: 4246522 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.1035. Min Act: -0.1700
Data Index: 1474904 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.1348. Min Act: -0.1700
Data Index: 267699 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.0723. Min Act: -0.1700
Data Index: 7413830 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.0410. Min Act: -0.1700
Data Index: 4891161 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6660. Min Range: -6.6660
Max Act: 6.0098. Min Act: -0.1700
Data Index: 2810918 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6660. Min Range: -6.6660
Max Act: 5.9473. Min Act: -0.1700
Data Index: 3833103 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6660. Min Range: -6.6660
Max Act: 5.9473. Min Act: -0.1700
Data Index: 1422204 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6660. Min Range: -6.6660
Max Act: 5.9473. Min Act: -0.1700
Data Index: 4970457 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6660. Min Range: -6.6660
Max Act: 5.9473. Min Act: -0.1700
Data Index: 6714659 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6660. Min Range: -6.6660
Max Act: 5.9785. Min Act: -0.1700
Data Index: 4873475 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6660. Min Range: -6.6660
Max Act: 5.9160. Min Act: -0.1700
Data Index: 7784588 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6660. Min Range: -6.6660
Max Act: 5.9160. Min Act: -0.1700
Data Index: 389048 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6660. Min Range: -6.6660
Max Act: 5.9160. Min Act: -0.1700
Data Index: 8780922 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6660. Min Range: -6.6660
Max Act: 5.9160. Min Act: -0.1700
Data Index: 1459860 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19