Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3327. Min Range: -9.3327
Max Act: 9.3327. Min Act: -0.1700
Data Index: 6693524 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.3327. Min Act: -0.1700
Data Index: 5000871 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.2702. Min Act: -0.1700
Data Index: 6795817 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.2702. Min Act: -0.1700
Data Index: 3057426 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.3327. Min Act: -0.1700
Data Index: 7861098 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.2702. Min Act: -0.1700
Data Index: 215141 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.2702. Min Act: -0.1700
Data Index: 431054 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.2702. Min Act: -0.1700
Data Index: 7442381 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.2077. Min Act: -0.1700
Data Index: 2771640 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.1452. Min Act: -0.1700
Data Index: 1289981 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.2077. Min Act: -0.1700
Data Index: 1191125 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.0827. Min Act: -0.1700
Data Index: 1018475 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.0202. Min Act: -0.1700
Data Index: 6570204 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.0202. Min Act: -0.1700
Data Index: 7163520 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.0202. Min Act: -0.1700
Data Index: 7779449 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.0202. Min Act: -0.1700
Data Index: 3827463 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.0202. Min Act: -0.1700
Data Index: 1629776 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.0202. Min Act: -0.1700
Data Index: 1758952 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3327. Min Range: -9.3327
Max Act: 8.0202. Min Act: -0.1700
Data Index: 6033612 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3327. Min Range: -9.3327
Max Act: 7.9577. Min Act: -0.1700
Data Index: 6964487 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19