Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.7695. Min Act: -0.1700
Data Index: 5484350 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6896. Min Act: -0.1700
Data Index: 6388870 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6736. Min Act: -0.1700
Data Index: 7574751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6254. Min Act: -0.1700
Data Index: 4717243 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6254. Min Act: -0.1700
Data Index: 3344355 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 8477630 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 3839476 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.5932. Min Act: -0.1700
Data Index: 7678521 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 2247780 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.5932. Min Act: -0.1700
Data Index: 6836857 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 4248796 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 2843726 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 6370974 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 6116088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 7921876 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 7878801 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 5738073 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.6093. Min Act: -0.1700
Data Index: 5236033 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.5932. Min Act: -0.1700
Data Index: 1782345 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7695. Min Range: -2.7695
Max Act: 2.5771. Min Act: -0.1700
Data Index: 6866453 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19