Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2859 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.8250. Min Act: -0.1700
Data Index: 1125502 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.7312. Min Act: -0.1700
Data Index: 1211366 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.7312. Min Act: -0.1700
Data Index: 4542709 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.6687. Min Act: -0.1700
Data Index: 1936751 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.6375. Min Act: -0.1700
Data Index: 2066243 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.6062. Min Act: -0.1700
Data Index: 5679934 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.5750. Min Act: -0.1700
Data Index: 8650055 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.5750. Min Act: -0.1700
Data Index: 5698233 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.5750. Min Act: -0.1700
Data Index: 7136153 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.5437. Min Act: -0.1700
Data Index: 3332778 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.5437. Min Act: -0.1700
Data Index: 4935327 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.5437. Min Act: -0.1700
Data Index: 3119072 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.5437. Min Act: -0.1700
Data Index: 373995 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.4812. Min Act: -0.1699
Data Index: 6775978 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.4812. Min Act: -0.1700
Data Index: 6775976 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.5125. Min Act: -0.1700
Data Index: 5786679 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.4500. Min Act: -0.1700
Data Index: 3642057 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.4500. Min Act: -0.1700
Data Index: 3862215 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.4187. Min Act: -0.1700
Data Index: 879843 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8250. Min Range: -5.8250
Max Act: 5.4187. Min Act: -0.1700
Data Index: 4612632 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19