Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1777 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0125. Min Range: -8.0125
Max Act: 8.0125. Min Act: -0.1700
Data Index: 2094996 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.8875. Min Act: -0.1700
Data Index: 1138641 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.8250. Min Act: -0.1700
Data Index: 5669644 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.7625. Min Act: -0.1700
Data Index: 308329 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.7625. Min Act: -0.1700
Data Index: 2094995 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.7000. Min Act: -0.1700
Data Index: 2078295 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.6062. Min Act: -0.1700
Data Index: 2181868 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.6375. Min Act: -0.1700
Data Index: 693092 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.6375. Min Act: -0.1700
Data Index: 4897776 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.5750. Min Act: -0.1700
Data Index: 3671615 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.5750. Min Act: -0.1700
Data Index: 1991009 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.5437. Min Act: -0.1700
Data Index: 2410290 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.5125. Min Act: -0.1700
Data Index: 1466168 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.5125. Min Act: -0.1700
Data Index: 5008010 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.4500. Min Act: -0.1700
Data Index: 499324 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.4500. Min Act: -0.1700
Data Index: 2094992 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.4500. Min Act: -0.1700
Data Index: 8011555 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.4187. Min Act: -0.1700
Data Index: 2410298 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.4812. Min Act: -0.1700
Data Index: 5376098 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0125. Min Range: -8.0125
Max Act: 7.4500. Min Act: -0.1700
Data Index: 7311184 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19