Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3307 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.3657. Min Act: -0.1700
Data Index: 2439893 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.3032. Min Act: -0.1700
Data Index: 2034503 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2719. Min Act: -0.1700
Data Index: 6356107 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2719. Min Act: -0.1700
Data Index: 8159871 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2407. Min Act: -0.1700
Data Index: 6074835 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2407. Min Act: -0.1700
Data Index: 8092853 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2407. Min Act: -0.1700
Data Index: 3796765 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 6810121 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1469. Min Act: -0.1700
Data Index: 5069736 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2094. Min Act: -0.1700
Data Index: 1208460 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 7763841 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 4348675 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 8307842 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 4837777 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.0844. Min Act: -0.1700
Data Index: 7948806 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1156. Min Act: -0.1700
Data Index: 7663396 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.0844. Min Act: -0.1700
Data Index: 6212616 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1156. Min Act: -0.1700
Data Index: 2353877 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.0844. Min Act: -0.1700
Data Index: 1959786 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1469. Min Act: -0.1700
Data Index: 6967745 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19