Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2373 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.9706. Min Act: -0.1700
Data Index: 4333825 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.9394. Min Act: -0.1700
Data Index: 2998142 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.9081. Min Act: -0.1700
Data Index: 284559 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.8769. Min Act: -0.1700
Data Index: 2554861 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.8456. Min Act: -0.1700
Data Index: 6268713 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.8144. Min Act: -0.1700
Data Index: 4486916 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.7831. Min Act: -0.1700
Data Index: 7306459 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.7519. Min Act: -0.1700
Data Index: 4324877 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.7206. Min Act: -0.1700
Data Index: 3024757 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.7206. Min Act: -0.1700
Data Index: 5549967 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.7206. Min Act: -0.1700
Data Index: 767578 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.6581. Min Act: -0.1700
Data Index: 2517468 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.6894. Min Act: -0.1700
Data Index: 7156203 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.6894. Min Act: -0.1700
Data Index: 5572081 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.6894. Min Act: -0.1700
Data Index: 424502 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.6581. Min Act: -0.1700
Data Index: 5182399 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.6269. Min Act: -0.1700
Data Index: 5716424 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.6269. Min Act: -0.1700
Data Index: 196096 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.6269. Min Act: -0.1700
Data Index: 1693940 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9706. Min Range: -5.9706
Max Act: 5.6269. Min Act: -0.1700
Data Index: 7847366 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19