Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2391 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1828. Min Range: -8.1828
Max Act: 8.1828. Min Act: -0.1700
Data Index: 1530203 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.8703. Min Act: -0.1700
Data Index: 4700199 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.8390. Min Act: -0.1700
Data Index: 695235 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.8078. Min Act: -0.1700
Data Index: 7509977 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.8078. Min Act: -0.1700
Data Index: 2703849 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.7453. Min Act: -0.1700
Data Index: 7563295 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.6828. Min Act: -0.1700
Data Index: 4761213 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.6515. Min Act: -0.1700
Data Index: 8719606 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.5578. Min Act: -0.1700
Data Index: 4977359 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.5578. Min Act: -0.1700
Data Index: 8227875 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.5265. Min Act: -0.1700
Data Index: 6066829 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.5265. Min Act: -0.1700
Data Index: 5761501 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.5265. Min Act: -0.1700
Data Index: 3859296 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.5265. Min Act: -0.1700
Data Index: 2293366 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.4640. Min Act: -0.1700
Data Index: 6278385 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 7557880 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.4640. Min Act: -0.1700
Data Index: 4650559 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 6583593 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.4328. Min Act: -0.1700
Data Index: 2333803 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1828. Min Range: -8.1828
Max Act: 7.4328. Min Act: -0.1700
Data Index: 6298646 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19