Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.8142. Min Act: -0.1700
Data Index: 3640962 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.7517. Min Act: -0.1700
Data Index: 2865701 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.8142. Min Act: -0.1700
Data Index: 4205221 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.3142. Min Act: -0.1700
Data Index: 3268942 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.2517. Min Act: -0.1700
Data Index: 6866453 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.2517. Min Act: -0.1700
Data Index: 7580387 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.1892. Min Act: -0.1700
Data Index: 8409245 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.1892. Min Act: -0.1700
Data Index: 7087060 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.1267. Min Act: -0.1700
Data Index: 5119356 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8142. Min Range: -9.8142
Max Act: 9.0017. Min Act: -0.1700
Data Index: 633648 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.9392. Min Act: -0.1700
Data Index: 2489872 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.8767. Min Act: -0.1700
Data Index: 2373243 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.8142. Min Act: -0.1700
Data Index: 6973788 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.7517. Min Act: -0.1700
Data Index: 7290211 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.7517. Min Act: -0.1700
Data Index: 8615146 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.7517. Min Act: -0.1700
Data Index: 1541751 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.8142. Min Act: -0.1700
Data Index: 7028492 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.7517. Min Act: -0.1700
Data Index: 6853040 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.7517. Min Act: -0.1700
Data Index: 5210834 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8142. Min Range: -9.8142
Max Act: 8.6892. Min Act: -0.1700
Data Index: 7303822 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19