Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.1310. Min Act: -0.1700
Data Index: 1941724 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9748. Min Act: -0.1700
Data Index: 3136889 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9748. Min Act: -0.1700
Data Index: 4172813 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9748. Min Act: -0.1700
Data Index: 446214 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0060. Min Act: -0.1700
Data Index: 665888 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9748. Min Act: -0.1700
Data Index: 2163770 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9748. Min Act: -0.1700
Data Index: 657070 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 1065637 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 5070880 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 1713463 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8498. Min Act: -0.1700
Data Index: 3371531 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 4910036 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 7494301 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 4889975 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 6792818 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 2947562 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 5986991 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 293223 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.7873. Min Act: -0.1700
Data Index: 1033798 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.7873. Min Act: -0.1700
Data Index: 4188933 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19