Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3961 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.6675. Min Act: -0.1700
Data Index: 2272448 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.6514. Min Act: -0.1700
Data Index: 6904321 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.6514. Min Act: -0.1700
Data Index: 134664 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.6193. Min Act: -0.1700
Data Index: 3246353 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.6193. Min Act: -0.1700
Data Index: 1956483 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.6193. Min Act: -0.1700
Data Index: 8617771 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5871. Min Act: -0.1700
Data Index: 7197787 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.6032. Min Act: -0.1700
Data Index: 8617773 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.6032. Min Act: -0.1700
Data Index: 2272449 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5871. Min Act: -0.1700
Data Index: 4157841 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5871. Min Act: -0.1700
Data Index: 2272450 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.6032. Min Act: -0.1700
Data Index: 3565126 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5710. Min Act: -0.1700
Data Index: 1049365 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5710. Min Act: -0.1700
Data Index: 1049366 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5387. Min Act: -0.1700
Data Index: 8617772 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5387. Min Act: -0.1700
Data Index: 5970575 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5064. Min Act: -0.1700
Data Index: 5667509 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5226. Min Act: -0.1700
Data Index: 5451458 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5226. Min Act: -0.1700
Data Index: 1196757 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6675. Min Range: -2.6675
Max Act: 2.5064. Min Act: -0.1700
Data Index: 1126100 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19