Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1591 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.2187. Min Act: -0.1700
Data Index: 151283 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1874. Min Act: -0.1700
Data Index: 5302499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1874. Min Act: -0.1698
Data Index: 7803790 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.2187. Min Act: -0.1700
Data Index: 3697025 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1874. Min Act: -0.1700
Data Index: 5302506 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1874. Min Act: -0.1700
Data Index: 7222070 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1562. Min Act: -0.1700
Data Index: 1572053 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1562. Min Act: -0.1700
Data Index: 5338406 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1562. Min Act: -0.1696
Data Index: 5302513 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1562. Min Act: -0.1699
Data Index: 5302510 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1562. Min Act: -0.1700
Data Index: 8608951 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1562. Min Act: -0.1700
Data Index: 8565534 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1562. Min Act: -0.1700
Data Index: 5302498 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1249. Min Act: -0.1700
Data Index: 3482709 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1249. Min Act: -0.1700
Data Index: 990415 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1249. Min Act: -0.1700
Data Index: 3229898 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.1249. Min Act: -0.1700
Data Index: 6629012 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.0937. Min Act: -0.1700
Data Index: 5302507 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.0937. Min Act: -0.1700
Data Index: 6372964 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2187. Min Range: -4.2187
Max Act: 4.0937. Min Act: -0.1700
Data Index: 3427363 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19