Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.9108. Min Act: -0.1698
Data Index: 7354094 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.9279. Min Act: -0.1696
Data Index: 8581045 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.9108. Min Act: -0.1683
Data Index: 4421570 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.8766. Min Act: -0.1698
Data Index: 5974632 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.8766. Min Act: -0.1673
Data Index: 5375840 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.8596. Min Act: -0.1694
Data Index: 2793362 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.8426. Min Act: -0.1691
Data Index: 5809477 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.8173. Min Act: -0.1673
Data Index: 509825 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.8257. Min Act: -0.1700
Data Index: 3877645 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7838. Min Act: -0.1689
Data Index: 4084039 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7838. Min Act: -0.1700
Data Index: 4163680 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7671. Min Act: -0.1697
Data Index: 2168251 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7588. Min Act: -0.1695
Data Index: 4327608 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7588. Min Act: -0.1700
Data Index: 1282347 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7588. Min Act: -0.1700
Data Index: 6911873 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7588. Min Act: -0.1700
Data Index: 4289867 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7588. Min Act: -0.1700
Data Index: 3380933 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7588. Min Act: -0.1700
Data Index: 6520786 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7754. Min Act: -0.1689
Data Index: 2128757 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9279. Min Range: -0.9279
Max Act: 0.7588. Min Act: -0.1697
Data Index: 1589222 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19