Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6346 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5100. Min Range: -9.5100
Max Act: 9.5100. Min Act: -0.1700
Data Index: 5768067 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5100. Min Range: -9.5100
Max Act: 9.3225. Min Act: -0.1700
Data Index: 5736414 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5100. Min Range: -9.5100
Max Act: 9.1975. Min Act: -0.1700
Data Index: 6045949 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5100. Min Range: -9.5100
Max Act: 9.1350. Min Act: -0.1700
Data Index: 2549512 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5100. Min Range: -9.5100
Max Act: 9.0100. Min Act: -0.1700
Data Index: 2234871 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5100. Min Range: -9.5100
Max Act: 9.0100. Min Act: -0.1700
Data Index: 5155986 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.9475. Min Act: -0.1700
Data Index: 290312 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.8225. Min Act: -0.1700
Data Index: 8078738 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.8225. Min Act: -0.1700
Data Index: 5029492 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.8225. Min Act: -0.1700
Data Index: 174322 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.8225. Min Act: -0.1700
Data Index: 8401871 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.6975. Min Act: -0.1700
Data Index: 1862954 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.6350. Min Act: -0.1700
Data Index: 5552384 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.6350. Min Act: -0.1700
Data Index: 4220326 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.5725. Min Act: -0.1700
Data Index: 3934984 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.6350. Min Act: -0.1700
Data Index: 5914552 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.6350. Min Act: -0.1700
Data Index: 5517834 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.5725. Min Act: -0.1700
Data Index: 1828735 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.5725. Min Act: -0.1700
Data Index: 4751981 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5100. Min Range: -9.5100
Max Act: 8.5100. Min Act: -0.1700
Data Index: 275102 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19