Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 346 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0841. Min Range: -6.0841
Max Act: 6.0841. Min Act: -0.1700
Data Index: 4640574 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.9591. Min Act: -0.1700
Data Index: 1207829 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.8654. Min Act: -0.1700
Data Index: 3917653 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.7716. Min Act: -0.1700
Data Index: 8315857 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.6779. Min Act: -0.1700
Data Index: 5848803 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.6466. Min Act: -0.1700
Data Index: 6522436 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.5841. Min Act: -0.1700
Data Index: 6322613 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.5529. Min Act: -0.1700
Data Index: 7404024 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.5216. Min Act: -0.1700
Data Index: 6812507 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.5216. Min Act: -0.1700
Data Index: 497396 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.4904. Min Act: -0.1700
Data Index: 4215629 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.4279. Min Act: -0.1700
Data Index: 1604010 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.4591. Min Act: -0.1700
Data Index: 4410 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.4591. Min Act: -0.1700
Data Index: 2063107 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.4591. Min Act: -0.1700
Data Index: 8363759 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.4591. Min Act: -0.1700
Data Index: 5810043 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.4591. Min Act: -0.1700
Data Index: 4870111 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.4279. Min Act: -0.1700
Data Index: 23388 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.3654. Min Act: -0.1700
Data Index: 377041 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.3966. Min Act: -0.1700
Data Index: 2999708 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19