Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2449 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0875. Min Act: -0.1700
Data Index: 1699130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0700. Min Act: -0.1700
Data Index: 6292975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0438. Min Act: -0.1700
Data Index: 5474845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0264. Min Act: -0.1700
Data Index: 6292979 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0351. Min Act: -0.1700
Data Index: 3884818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0177. Min Act: -0.1700
Data Index: 1005550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0177. Min Act: -0.1700
Data Index: 4922426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0177. Min Act: -0.1700
Data Index: 3283758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0177. Min Act: -0.1700
Data Index: 5437848 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0090. Min Act: -0.1700
Data Index: 7038443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0090. Min Act: -0.1700
Data Index: 3226846 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0090. Min Act: -0.1700
Data Index: 6221754 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0090. Min Act: -0.1700
Data Index: 3471776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0090. Min Act: -0.1700
Data Index: 937258 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0003. Min Act: -0.1700
Data Index: 1773096 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0003. Min Act: -0.1700
Data Index: 210017 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0875. Min Range: -1.0875
Max Act: 0.9917. Min Act: -0.1700
Data Index: 3968546 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0003. Min Act: -0.1700
Data Index: 785298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0003. Min Act: -0.1700
Data Index: 642752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0875. Min Range: -1.0875
Max Act: 1.0003. Min Act: -0.1700
Data Index: 5474846 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19