Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.9176. Min Act: -0.1700
Data Index: 1818814 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.8863. Min Act: -0.1700
Data Index: 2839317 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.6676. Min Act: -0.1700
Data Index: 479854 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.6363. Min Act: -0.1700
Data Index: 2837080 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.6051. Min Act: -0.1700
Data Index: 8179867 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.5738. Min Act: -0.1700
Data Index: 3264344 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.5426. Min Act: -0.1700
Data Index: 1466196 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.5738. Min Act: -0.1700
Data Index: 6632733 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.5113. Min Act: -0.1700
Data Index: 927928 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.5113. Min Act: -0.1700
Data Index: 4693630 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.4801. Min Act: -0.1700
Data Index: 6192879 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.4488. Min Act: -0.1700
Data Index: 2301680 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.4488. Min Act: -0.1700
Data Index: 3746278 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.4176. Min Act: -0.1700
Data Index: 4441527 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.4176. Min Act: -0.1700
Data Index: 774248 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.3863. Min Act: -0.1700
Data Index: 6938492 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.3863. Min Act: -0.1700
Data Index: 7808314 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.3863. Min Act: -0.1700
Data Index: 7970183 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.3863. Min Act: -0.1700
Data Index: 1754494 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9176. Min Range: -4.9176
Max Act: 4.3863. Min Act: -0.1700
Data Index: 4374883 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19