Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.7523. Min Act: -0.1700
Data Index: 1054970 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.5648. Min Act: -0.1700
Data Index: 6389287 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.6273. Min Act: -0.1700
Data Index: 1736237 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.5023. Min Act: -0.1700
Data Index: 1197309 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.4398. Min Act: -0.1700
Data Index: 6343573 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.4398. Min Act: -0.1700
Data Index: 3772279 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.4398. Min Act: -0.1700
Data Index: 3907934 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.4398. Min Act: -0.1700
Data Index: 5840657 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.4398. Min Act: -0.1700
Data Index: 5617234 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.4398. Min Act: -0.1700
Data Index: 6486891 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.3773. Min Act: -0.1700
Data Index: 1851707 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.3148. Min Act: -0.1700
Data Index: 3947512 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.3148. Min Act: -0.1700
Data Index: 2650019 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.3148. Min Act: -0.1700
Data Index: 3695363 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.3148. Min Act: -0.1700
Data Index: 8336728 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.3148. Min Act: -0.1700
Data Index: 3654658 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.3148. Min Act: -0.1700
Data Index: 1327197 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.3148. Min Act: -0.1700
Data Index: 8370057 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.2523. Min Act: -0.1700
Data Index: 5268113 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7523. Min Range: -8.7523
Max Act: 8.2523. Min Act: -0.1700
Data Index: 4788855 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19