Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2260. Min Range: -5.2260
Max Act: 5.2260. Min Act: -0.1700
Data Index: 3205784 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.5697. Min Act: -0.1700
Data Index: 5400349 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.5385. Min Act: -0.1700
Data Index: 5284740 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.5385. Min Act: -0.1700
Data Index: 4833281 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.5697. Min Act: -0.1700
Data Index: 6927386 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.5385. Min Act: -0.1700
Data Index: 7872096 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.5385. Min Act: -0.1700
Data Index: 2885910 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.5072. Min Act: -0.1700
Data Index: 2243784 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.5072. Min Act: -0.1700
Data Index: 648771 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4760. Min Act: -0.1700
Data Index: 4833270 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4447. Min Act: -0.1700
Data Index: 2047296 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4447. Min Act: -0.1700
Data Index: 2120122 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4135. Min Act: -0.1700
Data Index: 3581848 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4760. Min Act: -0.1700
Data Index: 7320370 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4447. Min Act: -0.1700
Data Index: 499856 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4447. Min Act: -0.1700
Data Index: 3975761 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.3822. Min Act: -0.1700
Data Index: 462442 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4135. Min Act: -0.1700
Data Index: 1436586 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4135. Min Act: -0.1700
Data Index: 1577368 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2260. Min Range: -5.2260
Max Act: 4.4135. Min Act: -0.1700
Data Index: 5063586 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19