Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 739 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.9517. Min Act: -0.1700
Data Index: 971689 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0142. Min Range: -8.0142
Max Act: 8.0142. Min Act: -0.1700
Data Index: 6982333 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.9517. Min Act: -0.1700
Data Index: 8557907 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.8892. Min Act: -0.1700
Data Index: 3001191 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.7642. Min Act: -0.1700
Data Index: 3800759 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.6704. Min Act: -0.1700
Data Index: 598703 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.6704. Min Act: -0.1700
Data Index: 3029855 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.6079. Min Act: -0.1700
Data Index: 4600595 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.6392. Min Act: -0.1700
Data Index: 4207658 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.5767. Min Act: -0.1700
Data Index: 5403169 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.6392. Min Act: -0.1700
Data Index: 3824070 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.5767. Min Act: -0.1700
Data Index: 6313625 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.6079. Min Act: -0.1700
Data Index: 7459855 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.6079. Min Act: -0.1700
Data Index: 8350812 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.5767. Min Act: -0.1700
Data Index: 470857 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.5767. Min Act: -0.1700
Data Index: 7743587 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.5142. Min Act: -0.1700
Data Index: 4006447 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.4829. Min Act: -0.1700
Data Index: 3319489 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.4829. Min Act: -0.1700
Data Index: 5333810 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0142. Min Range: -8.0142
Max Act: 7.5767. Min Act: -0.1700
Data Index: 3643128 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19