Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 345 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.8353. Min Act: -0.1700
Data Index: 1207635 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.6478. Min Act: -0.1700
Data Index: 2407007 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.4603. Min Act: -0.1700
Data Index: 3977708 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.3978. Min Act: -0.1700
Data Index: 2281024 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.4603. Min Act: -0.1700
Data Index: 5123610 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.3978. Min Act: -0.1700
Data Index: 2574062 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.3353. Min Act: -0.1700
Data Index: 1383694 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.2103. Min Act: -0.1700
Data Index: 575775 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.2728. Min Act: -0.1700
Data Index: 8737159 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.2728. Min Act: -0.1700
Data Index: 642538 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.2103. Min Act: -0.1700
Data Index: 8025923 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.2103. Min Act: -0.1700
Data Index: 2996956 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.1478. Min Act: -0.1700
Data Index: 7063138 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.1478. Min Act: -0.1700
Data Index: 3633091 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.0853. Min Act: -0.1700
Data Index: 2566368 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.1478. Min Act: -0.1700
Data Index: 281357 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.0853. Min Act: -0.1700
Data Index: 8279209 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.0853. Min Act: -0.1700
Data Index: 1204791 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.0228. Min Act: -0.1700
Data Index: 459929 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8353. Min Range: -9.8353
Max Act: 9.0853. Min Act: -0.1700
Data Index: 1608758 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19