Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0110. Min Range: -5.0110
Max Act: 5.0110. Min Act: -0.1700
Data Index: 5393210 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.7298. Min Act: -0.1700
Data Index: 800890 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.6048. Min Act: -0.1700
Data Index: 123757 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.6048. Min Act: -0.1700
Data Index: 4029543 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.5110. Min Act: -0.1700
Data Index: 1555078 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.5110. Min Act: -0.1700
Data Index: 3333736 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4485. Min Act: -0.1700
Data Index: 7058530 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4798. Min Act: -0.1700
Data Index: 33979 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4485. Min Act: -0.1700
Data Index: 4249765 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3860. Min Act: -0.1700
Data Index: 6054002 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3860. Min Act: -0.1700
Data Index: 7934445 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3548. Min Act: -0.1700
Data Index: 6509852 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3548. Min Act: -0.1700
Data Index: 6448299 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3548. Min Act: -0.1700
Data Index: 3277740 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3548. Min Act: -0.1700
Data Index: 800889 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3548. Min Act: -0.1700
Data Index: 5742656 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3548. Min Act: -0.1700
Data Index: 3151895 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3548. Min Act: -0.1700
Data Index: 3050289 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3548. Min Act: -0.1700
Data Index: 642652 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.3235. Min Act: -0.1700
Data Index: 2153608 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19