Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4166 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.8556. Min Act: -0.1700
Data Index: 8615889 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.5431. Min Act: -0.1700
Data Index: 8552883 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.5431. Min Act: -0.1700
Data Index: 498350 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.3556. Min Act: -0.1700
Data Index: 2702140 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.3556. Min Act: -0.1700
Data Index: 7366507 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.2931. Min Act: -0.1700
Data Index: 4475586 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.2618. Min Act: -0.1700
Data Index: 7464424 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.2618. Min Act: -0.1700
Data Index: 4924125 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.1993. Min Act: -0.1700
Data Index: 1237187 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.1681. Min Act: -0.1700
Data Index: 5198984 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.1368. Min Act: -0.1700
Data Index: 4248264 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.1056. Min Act: -0.1700
Data Index: 5426970 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.1056. Min Act: -0.1700
Data Index: 2165334 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.1056. Min Act: -0.1700
Data Index: 4947763 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.1056. Min Act: -0.1700
Data Index: 1956614 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.0743. Min Act: -0.1700
Data Index: 5930284 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.1056. Min Act: -0.1700
Data Index: 5841812 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.0743. Min Act: -0.1700
Data Index: 4872470 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.0743. Min Act: -0.1700
Data Index: 5056193 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8556. Min Range: -7.8556
Max Act: 7.0743. Min Act: -0.1700
Data Index: 2155248 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19