Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1424 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.9431. Min Act: -0.1700
Data Index: 4485330 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0056. Min Range: -8.0056
Max Act: 8.0056. Min Act: -0.1700
Data Index: 2654490 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.7556. Min Act: -0.1700
Data Index: 5948902 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.6306. Min Act: -0.1700
Data Index: 4407637 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.5993. Min Act: -0.1700
Data Index: 2631231 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.5368. Min Act: -0.1700
Data Index: 1297356 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.5056. Min Act: -0.1700
Data Index: 8773961 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.4743. Min Act: -0.1700
Data Index: 2578495 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.4118. Min Act: -0.1700
Data Index: 4407644 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.2556. Min Act: -0.1700
Data Index: 1614760 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.2243. Min Act: -0.1700
Data Index: 8515454 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.1931. Min Act: -0.1700
Data Index: 5887291 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.1931. Min Act: -0.1700
Data Index: 4884599 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.0993. Min Act: -0.1700
Data Index: 1990380 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.0056. Min Act: -0.1700
Data Index: 1692072 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.0681. Min Act: -0.1700
Data Index: 4658570 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.0056. Min Act: -0.1700
Data Index: 904950 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.0056. Min Act: -0.1700
Data Index: 2098190 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0056. Min Range: -8.0056
Max Act: 6.9431. Min Act: -0.1700
Data Index: 1691431 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0056. Min Range: -8.0056
Max Act: 6.9431. Min Act: -0.1700
Data Index: 8215700 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19