Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4894 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4034. Min Range: -4.4034
Max Act: 4.4034. Min Act: -0.1700
Data Index: 4798125 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4034. Min Range: -4.4034
Max Act: 4.1222. Min Act: -0.1700
Data Index: 3062285 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4034. Min Range: -4.4034
Max Act: 4.0284. Min Act: -0.1700
Data Index: 1945018 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.9971. Min Act: -0.1700
Data Index: 7519859 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.9346. Min Act: -0.1700
Data Index: 930730 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.9033. Min Act: -0.1700
Data Index: 4057484 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.9033. Min Act: -0.1700
Data Index: 8409818 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.9033. Min Act: -0.1700
Data Index: 7467338 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.9033. Min Act: -0.1700
Data Index: 2678167 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8408. Min Act: -0.1700
Data Index: 8359731 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8721. Min Act: -0.1700
Data Index: 5451080 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8721. Min Act: -0.1700
Data Index: 1088263 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8721. Min Act: -0.1700
Data Index: 2553852 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8408. Min Act: -0.1700
Data Index: 7611748 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8721. Min Act: -0.1700
Data Index: 5630573 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8252. Min Act: -0.1700
Data Index: 5872407 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8408. Min Act: -0.1700
Data Index: 2482666 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8252. Min Act: -0.1700
Data Index: 4952913 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8252. Min Act: -0.1700
Data Index: 5922764 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4034. Min Range: -4.4034
Max Act: 3.8095. Min Act: -0.1700
Data Index: 4206432 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19