Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4561 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.4667. Min Act: -0.1700
Data Index: 6392013 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1855. Min Act: -0.1700
Data Index: 4394952 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1542. Min Act: -0.1700
Data Index: 105107 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 5576678 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 7872189 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1229. Min Act: -0.1700
Data Index: 4415223 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0917. Min Act: -0.1700
Data Index: 8240029 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0917. Min Act: -0.1700
Data Index: 1026775 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0604. Min Act: -0.1700
Data Index: 7265306 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0604. Min Act: -0.1700
Data Index: 8476277 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0604. Min Act: -0.1700
Data Index: 187000 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0292. Min Act: -0.1700
Data Index: 7023061 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0292. Min Act: -0.1700
Data Index: 2451990 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0604. Min Act: -0.1700
Data Index: 3990605 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0292. Min Act: -0.1700
Data Index: 7241388 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4667. Min Range: -4.4667
Max Act: 3.9979. Min Act: -0.1700
Data Index: 5785011 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4667. Min Range: -4.4667
Max Act: 3.9979. Min Act: -0.1700
Data Index: 5534751 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4667. Min Range: -4.4667
Max Act: 3.9666. Min Act: -0.1700
Data Index: 5297689 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4667. Min Range: -4.4667
Max Act: 3.9979. Min Act: -0.1700
Data Index: 8260988 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4667. Min Range: -4.4667
Max Act: 3.9979. Min Act: -0.1700
Data Index: 5139771 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19