Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2643. Min Range: -8.2643
Max Act: 8.2643. Min Act: -0.1700
Data Index: 6459166 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.8268. Min Act: -0.1700
Data Index: 800247 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.7643. Min Act: -0.1700
Data Index: 6584733 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.5768. Min Act: -0.1700
Data Index: 4832023 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.5143. Min Act: -0.1700
Data Index: 6830455 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.4831. Min Act: -0.1700
Data Index: 5973686 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.4518. Min Act: -0.1700
Data Index: 107546 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.2643. Min Act: -0.1700
Data Index: 4238855 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.2643. Min Act: -0.1700
Data Index: 1598202 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.2643. Min Act: -0.1700
Data Index: 1913205 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.2331. Min Act: -0.1700
Data Index: 1232682 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.2331. Min Act: -0.1700
Data Index: 3567393 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.2018. Min Act: -0.1700
Data Index: 2233200 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.2018. Min Act: -0.1700
Data Index: 6642478 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.1706. Min Act: -0.1700
Data Index: 1075894 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.1706. Min Act: -0.1700
Data Index: 57853 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.1706. Min Act: -0.1700
Data Index: 5368070 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.1393. Min Act: -0.1700
Data Index: 7832502 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.1081. Min Act: -0.1700
Data Index: 5492110 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2643. Min Range: -8.2643
Max Act: 7.1081. Min Act: -0.1700
Data Index: 7098942 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19