Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.1353. Min Act: -0.1700
Data Index: 7598027 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.1089. Min Act: -0.1700
Data Index: 7802074 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0827. Min Act: -0.1700
Data Index: 8342112 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0652. Min Act: -0.1686
Data Index: 7465045 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0652. Min Act: -0.1700
Data Index: 1077395 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0652. Min Act: -0.1700
Data Index: 7827121 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0390. Min Act: -0.1700
Data Index: 5240951 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0390. Min Act: -0.1700
Data Index: 3977827 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0303. Min Act: -0.1700
Data Index: 8724270 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0303. Min Act: -0.1700
Data Index: 3093701 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0216. Min Act: -0.1700
Data Index: 3211857 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0216. Min Act: -0.1699
Data Index: 3375664 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0216. Min Act: -0.1700
Data Index: 7962123 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0216. Min Act: -0.1700
Data Index: 1138743 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0303. Min Act: -0.1681
Data Index: 949105 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0042. Min Act: -0.1700
Data Index: 7970052 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1353. Min Range: -1.1353
Max Act: 0.9955. Min Act: -0.1698
Data Index: 3874616 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0129. Min Act: -0.1699
Data Index: 3738307 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1353. Min Range: -1.1353
Max Act: 1.0042. Min Act: -0.1700
Data Index: 3632652 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1353. Min Range: -1.1353
Max Act: 0.9955. Min Act: -0.1699
Data Index: 7751830 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19