Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0817. Min Range: -7.0817
Max Act: 7.0817. Min Act: -0.1700
Data Index: 84563 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.9567. Min Act: -0.1700
Data Index: 1641322 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.9567. Min Act: -0.1700
Data Index: 950222 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.8317. Min Act: -0.1700
Data Index: 6531776 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7692. Min Act: -0.1700
Data Index: 4527543 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7692. Min Act: -0.1700
Data Index: 3612088 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7380. Min Act: -0.1700
Data Index: 7186607 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7067. Min Act: -0.1700
Data Index: 928842 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7692. Min Act: -0.1700
Data Index: 764739 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7692. Min Act: -0.1700
Data Index: 8603494 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7067. Min Act: -0.1700
Data Index: 2447445 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7067. Min Act: -0.1700
Data Index: 7899143 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.6755. Min Act: -0.1700
Data Index: 8159757 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.6755. Min Act: -0.1700
Data Index: 3819000 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7380. Min Act: -0.1700
Data Index: 3097288 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.6755. Min Act: -0.1700
Data Index: 8219424 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.7067. Min Act: -0.1700
Data Index: 5936466 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.6755. Min Act: -0.1700
Data Index: 3845187 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.6442. Min Act: -0.1700
Data Index: 235273 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0817. Min Range: -7.0817
Max Act: 6.6442. Min Act: -0.1700
Data Index: 2069579 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19