Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5286 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.3500. Min Act: -0.1700
Data Index: 3257974 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.3188. Min Act: -0.1700
Data Index: 3317681 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.3188. Min Act: -0.1700
Data Index: 8608732 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.2250. Min Act: -0.1700
Data Index: 4913069 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.2250. Min Act: -0.1700
Data Index: 2125 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.1625. Min Act: -0.1700
Data Index: 6697167 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.1313. Min Act: -0.1700
Data Index: 8125307 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.1313. Min Act: -0.1700
Data Index: 5738638 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.1313. Min Act: -0.1700
Data Index: 4971790 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.1000. Min Act: -0.1700
Data Index: 5159414 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.1000. Min Act: -0.1700
Data Index: 3240569 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.0688. Min Act: -0.1700
Data Index: 3316528 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.1000. Min Act: -0.1700
Data Index: 4498736 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.0063. Min Act: -0.1700
Data Index: 8398429 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.0063. Min Act: -0.1700
Data Index: 6172798 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.0063. Min Act: -0.1700
Data Index: 5906568 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.0063. Min Act: -0.1700
Data Index: 5833544 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3500. Min Range: -6.3500
Max Act: 6.0063. Min Act: -0.1700
Data Index: 5632395 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3500. Min Range: -6.3500
Max Act: 5.9750. Min Act: -0.1700
Data Index: 3008647 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3500. Min Range: -6.3500
Max Act: 5.9750. Min Act: -0.1700
Data Index: 1825416 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19