Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5327 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.5831. Min Act: -0.1700
Data Index: 8722477 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2706. Min Act: -0.1700
Data Index: 998496 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2706. Min Act: -0.1700
Data Index: 6097816 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.1769. Min Act: -0.1700
Data Index: 4335289 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.1144. Min Act: -0.1700
Data Index: 3592613 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.1144. Min Act: -0.1700
Data Index: 4063069 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0831. Min Act: -0.1700
Data Index: 7540236 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0831. Min Act: -0.1700
Data Index: 8511019 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0519. Min Act: -0.1700
Data Index: 1257400 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0519. Min Act: -0.1700
Data Index: 206438 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0519. Min Act: -0.1700
Data Index: 8665185 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0519. Min Act: -0.1700
Data Index: 1078734 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0519. Min Act: -0.1700
Data Index: 4663639 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0831. Min Act: -0.1700
Data Index: 956327 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0519. Min Act: -0.1700
Data Index: 6458691 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0519. Min Act: -0.1700
Data Index: 3254080 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0206. Min Act: -0.1700
Data Index: 944618 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0206. Min Act: -0.1700
Data Index: 7896840 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.0206. Min Act: -0.1700
Data Index: 623007 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5831. Min Range: -5.5831
Max Act: 4.9894. Min Act: -0.1700
Data Index: 5936262 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19