Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0640. Min Range: -9.0640
Max Act: 9.0640. Min Act: -0.1700
Data Index: 3314562 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.4390. Min Act: -0.1700
Data Index: 5610783 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.3765. Min Act: -0.1700
Data Index: 8602679 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.3140. Min Act: -0.1700
Data Index: 1757327 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.1265. Min Act: -0.1700
Data Index: 3942246 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.1890. Min Act: -0.1700
Data Index: 6352763 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.0640. Min Act: -0.1700
Data Index: 1606934 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.1265. Min Act: -0.1700
Data Index: 6204045 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.1265. Min Act: -0.1700
Data Index: 4548268 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.1890. Min Act: -0.1700
Data Index: 237338 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.0640. Min Act: -0.1700
Data Index: 3573366 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.0640. Min Act: -0.1700
Data Index: 4950248 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.0640. Min Act: -0.1700
Data Index: 1183175 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.0640. Min Act: -0.1700
Data Index: 3213060 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.0640. Min Act: -0.1700
Data Index: 8568825 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.0640. Min Act: -0.1700
Data Index: 3881711 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.0640. Min Act: -0.1700
Data Index: 4610257 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0640. Min Range: -9.0640
Max Act: 8.0015. Min Act: -0.1700
Data Index: 523116 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0640. Min Range: -9.0640
Max Act: 7.9390. Min Act: -0.1700
Data Index: 7963689 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0640. Min Range: -9.0640
Max Act: 7.9390. Min Act: -0.1700
Data Index: 832067 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19