Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1218 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0610. Min Range: -6.0610
Max Act: 6.0610. Min Act: -0.1700
Data Index: 6034488 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0610. Min Range: -6.0610
Max Act: 6.0298. Min Act: -0.1700
Data Index: 3294313 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0610. Min Range: -6.0610
Max Act: 6.0298. Min Act: -0.1700
Data Index: 1049009 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0610. Min Range: -6.0610
Max Act: 6.0298. Min Act: -0.1700
Data Index: 8296297 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.9985. Min Act: -0.1700
Data Index: 3850 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.9673. Min Act: -0.1700
Data Index: 5128209 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.9673. Min Act: -0.1700
Data Index: 6670712 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.9360. Min Act: -0.1700
Data Index: 4239718 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.9673. Min Act: -0.1700
Data Index: 3657028 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.9360. Min Act: -0.1700
Data Index: 4609313 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.9048. Min Act: -0.1700
Data Index: 6994039 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.8735. Min Act: -0.1700
Data Index: 8776655 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.8735. Min Act: -0.1700
Data Index: 1102178 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.8423. Min Act: -0.1700
Data Index: 3069395 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.8735. Min Act: -0.1700
Data Index: 2459200 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.8735. Min Act: -0.1700
Data Index: 7670901 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.8423. Min Act: -0.1700
Data Index: 6052169 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.8423. Min Act: -0.1700
Data Index: 7671660 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.8110. Min Act: -0.1700
Data Index: 3978543 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0610. Min Range: -6.0610
Max Act: 5.8423. Min Act: -0.1700
Data Index: 6792546 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19