Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1155. Min Range: -4.1155
Max Act: 4.1155. Min Act: -0.1700
Data Index: 3873906 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1155. Min Range: -4.1155
Max Act: 4.0842. Min Act: -0.1700
Data Index: 991519 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1155. Min Range: -4.1155
Max Act: 4.0217. Min Act: -0.1700
Data Index: 7109495 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.9279. Min Act: -0.1700
Data Index: 1130804 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.9279. Min Act: -0.1700
Data Index: 1557609 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.8966. Min Act: -0.1700
Data Index: 5449034 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.8966. Min Act: -0.1700
Data Index: 1553806 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.8341. Min Act: -0.1700
Data Index: 8705220 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.8654. Min Act: -0.1700
Data Index: 8367409 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.8341. Min Act: -0.1700
Data Index: 2201573 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.8341. Min Act: -0.1700
Data Index: 5409999 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.8028. Min Act: -0.1700
Data Index: 2585747 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.8028. Min Act: -0.1700
Data Index: 2898146 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.7716. Min Act: -0.1700
Data Index: 4765617 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.7716. Min Act: -0.1700
Data Index: 6654897 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.7403. Min Act: -0.1700
Data Index: 7926146 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.7403. Min Act: -0.1700
Data Index: 6813650 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.7090. Min Act: -0.1700
Data Index: 471932 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.7090. Min Act: -0.1700
Data Index: 6813147 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1155. Min Range: -4.1155
Max Act: 3.7403. Min Act: -0.1700
Data Index: 1764040 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19