Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2432 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7738. Min Range: -12.7738
Max Act: 12.7738. Min Act: -0.1700
Data Index: 1561528 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7738. Min Range: -12.7738
Max Act: 12.2113. Min Act: -0.1700
Data Index: 4216364 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7738. Min Range: -12.7738
Max Act: 12.0238. Min Act: -0.1700
Data Index: 8231776 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.9613. Min Act: -0.1700
Data Index: 5242648 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.8988. Min Act: -0.1700
Data Index: 3382254 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.8988. Min Act: -0.1700
Data Index: 7111387 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.8988. Min Act: -0.1700
Data Index: 6504981 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.8988. Min Act: -0.1700
Data Index: 1172612 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.8363. Min Act: -0.1700
Data Index: 6834610 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.8363. Min Act: -0.1700
Data Index: 7247714 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.7113. Min Act: -0.1700
Data Index: 5655775 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.7738. Min Act: -0.1700
Data Index: 5207813 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.7738. Min Act: -0.1700
Data Index: 8102487 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.7738. Min Act: -0.1700
Data Index: 7183179 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.7113. Min Act: -0.1700
Data Index: 5207815 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.7113. Min Act: -0.1699
Data Index: 495379 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.6488. Min Act: -0.1700
Data Index: 2985290 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.6488. Min Act: -0.1700
Data Index: 7823817 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.6488. Min Act: -0.1700
Data Index: 5501920 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7738. Min Range: -12.7738
Max Act: 11.5863. Min Act: -0.1700
Data Index: 7794488 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19