Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.7301. Min Act: -0.1700
Data Index: 7917798 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.7301. Min Act: -0.1700
Data Index: 4777496 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.6989. Min Act: -0.1700
Data Index: 2367763 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.6676. Min Act: -0.1700
Data Index: 3942694 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.6364. Min Act: -0.1700
Data Index: 8399887 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.6051. Min Act: -0.1700
Data Index: 5277766 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.5739. Min Act: -0.1700
Data Index: 6424164 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.5426. Min Act: -0.1700
Data Index: 7373798 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.5114. Min Act: -0.1700
Data Index: 5566449 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.5114. Min Act: -0.1700
Data Index: 3532375 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.5426. Min Act: -0.1700
Data Index: 6676078 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.4801. Min Act: -0.1700
Data Index: 1818353 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.4489. Min Act: -0.1700
Data Index: 5445088 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.4176. Min Act: -0.1700
Data Index: 4327171 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.4489. Min Act: -0.1700
Data Index: 1458773 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.4489. Min Act: -0.1700
Data Index: 3617145 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.4176. Min Act: -0.1700
Data Index: 7614434 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.4176. Min Act: -0.1700
Data Index: 7681595 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.4176. Min Act: -0.1700
Data Index: 3254845 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7301. Min Range: -6.7301
Max Act: 6.4176. Min Act: -0.1700
Data Index: 154565 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19