Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1438 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4997. Min Range: -9.4997
Max Act: 9.4997. Min Act: -0.1700
Data Index: 8622996 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4997. Min Range: -9.4997
Max Act: 9.1247. Min Act: -0.1700
Data Index: 98497 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4997. Min Range: -9.4997
Max Act: 8.3747. Min Act: -0.1700
Data Index: 1478058 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4997. Min Range: -9.4997
Max Act: 8.3122. Min Act: -0.1700
Data Index: 8537552 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4997. Min Range: -9.4997
Max Act: 8.2497. Min Act: -0.1700
Data Index: 1884798 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4997. Min Range: -9.4997
Max Act: 8.1247. Min Act: -0.1700
Data Index: 1859555 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4997. Min Range: -9.4997
Max Act: 8.0934. Min Act: -0.1700
Data Index: 1410198 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4997. Min Range: -9.4997
Max Act: 8.0622. Min Act: -0.1700
Data Index: 6364930 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4997. Min Range: -9.4997
Max Act: 8.0309. Min Act: -0.1700
Data Index: 1567768 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4997. Min Range: -9.4997
Max Act: 8.0309. Min Act: -0.1700
Data Index: 6883503 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9997. Min Act: -0.1700
Data Index: 4102443 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9684. Min Act: -0.1700
Data Index: 7472706 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9997. Min Act: -0.1700
Data Index: 5869864 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9684. Min Act: -0.1700
Data Index: 4866046 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9372. Min Act: -0.1700
Data Index: 1975204 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9372. Min Act: -0.1700
Data Index: 2666187 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9372. Min Act: -0.1700
Data Index: 3675367 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9372. Min Act: -0.1700
Data Index: 1580405 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9059. Min Act: -0.1700
Data Index: 245320 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4997. Min Range: -9.4997
Max Act: 7.9059. Min Act: -0.1700
Data Index: 640198 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19