Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.5822. Min Act: -0.1700
Data Index: 2138551 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.5822. Min Act: -0.1700
Data Index: 7672505 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.5822. Min Act: -0.1700
Data Index: 7013074 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.5661. Min Act: -0.1700
Data Index: 2138549 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.5176. Min Act: -0.1700
Data Index: 7013077 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.5015. Min Act: -0.1700
Data Index: 7013071 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.5015. Min Act: -0.1700
Data Index: 2138548 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4852. Min Act: -0.1700
Data Index: 1245869 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4852. Min Act: -0.1700
Data Index: 619376 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4690. Min Act: -0.1700
Data Index: 1245870 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4690. Min Act: -0.1700
Data Index: 7013067 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4528. Min Act: -0.1700
Data Index: 7013078 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4690. Min Act: -0.1700
Data Index: 7013072 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4365. Min Act: -0.1700
Data Index: 1071669 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4365. Min Act: -0.1700
Data Index: 7013060 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4365. Min Act: -0.1700
Data Index: 5361258 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4365. Min Act: -0.1700
Data Index: 8414761 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.4039. Min Act: -0.1700
Data Index: 5022295 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.3876. Min Act: -0.1700
Data Index: 5139702 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5822. Min Range: -2.5822
Max Act: 2.3712. Min Act: -0.1700
Data Index: 6452667 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19