Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.7716. Min Act: -0.1700
Data Index: 1902542 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.6779. Min Act: -0.1700
Data Index: 96328 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.6779. Min Act: -0.1700
Data Index: 8747160 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.6154. Min Act: -0.1700
Data Index: 924438 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.6466. Min Act: -0.1700
Data Index: 6854114 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.5841. Min Act: -0.1700
Data Index: 5023605 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.5841. Min Act: -0.1700
Data Index: 6514304 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.5841. Min Act: -0.1700
Data Index: 4122401 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.5529. Min Act: -0.1700
Data Index: 2837692 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.5216. Min Act: -0.1700
Data Index: 5650053 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.5216. Min Act: -0.1700
Data Index: 488067 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.5216. Min Act: -0.1700
Data Index: 6195818 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.5216. Min Act: -0.1700
Data Index: 720535 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.5529. Min Act: -0.1700
Data Index: 7536235 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.4904. Min Act: -0.1700
Data Index: 4879073 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.4904. Min Act: -0.1700
Data Index: 4955292 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.4904. Min Act: -0.1700
Data Index: 7284459 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.4591. Min Act: -0.1700
Data Index: 3589743 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.4591. Min Act: -0.1700
Data Index: 924437 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7716. Min Range: -4.7716
Max Act: 4.4591. Min Act: -0.1700
Data Index: 462145 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19