Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3970 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.4238. Min Act: -0.1700
Data Index: 5289636 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.4238. Min Act: -0.1700
Data Index: 364601 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.4238. Min Act: -0.1700
Data Index: 828600 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.3613. Min Act: -0.1700
Data Index: 7490726 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.3613. Min Act: -0.1700
Data Index: 3475788 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.2988. Min Act: -0.1700
Data Index: 4653011 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.2988. Min Act: -0.1700
Data Index: 5877695 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.2363. Min Act: -0.1700
Data Index: 5336469 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.2363. Min Act: -0.1700
Data Index: 6114570 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.1738. Min Act: -0.1700
Data Index: 6431493 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.1113. Min Act: -0.1700
Data Index: 4906816 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.1113. Min Act: -0.1700
Data Index: 3207995 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.1738. Min Act: -0.1700
Data Index: 7410675 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.1113. Min Act: -0.1700
Data Index: 3357649 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4238. Min Range: -8.4238
Max Act: 8.0488. Min Act: -0.1700
Data Index: 6711820 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4238. Min Range: -8.4238
Max Act: 7.9863. Min Act: -0.1700
Data Index: 7057150 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4238. Min Range: -8.4238
Max Act: 7.9551. Min Act: -0.1700
Data Index: 7674224 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4238. Min Range: -8.4238
Max Act: 7.9863. Min Act: -0.1700
Data Index: 3830486 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4238. Min Range: -8.4238
Max Act: 7.9863. Min Act: -0.1700
Data Index: 8150082 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4238. Min Range: -8.4238
Max Act: 7.9863. Min Act: -0.1700
Data Index: 1977897 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19