Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6162 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2986. Min Range: -8.2986
Max Act: 8.2986. Min Act: -0.1700
Data Index: 4711680 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.8611. Min Act: -0.1700
Data Index: 5495041 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.8611. Min Act: -0.1700
Data Index: 7022724 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.7986. Min Act: -0.1700
Data Index: 4314217 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.8611. Min Act: -0.1700
Data Index: 3454103 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.7986. Min Act: -0.1700
Data Index: 1315122 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.7986. Min Act: -0.1700
Data Index: 6437742 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.7361. Min Act: -0.1700
Data Index: 4156727 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.7361. Min Act: -0.1700
Data Index: 4703096 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.6736. Min Act: -0.1700
Data Index: 1659482 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.5798. Min Act: -0.1700
Data Index: 2355110 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.5486. Min Act: -0.1700
Data Index: 5471820 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.5486. Min Act: -0.1700
Data Index: 4727744 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.4548. Min Act: -0.1700
Data Index: 7199428 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.4548. Min Act: -0.1700
Data Index: 3747097 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.4548. Min Act: -0.1700
Data Index: 6508303 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.4548. Min Act: -0.1700
Data Index: 8285282 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.4548. Min Act: -0.1700
Data Index: 1193025 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.4548. Min Act: -0.1700
Data Index: 8802307 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2986. Min Range: -8.2986
Max Act: 7.4548. Min Act: -0.1700
Data Index: 6993720 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19