Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3742 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1640. Min Range: -7.1640
Max Act: 7.1640. Min Act: -0.1700
Data Index: 1457813 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1640. Min Range: -7.1640
Max Act: 7.0078. Min Act: -0.1700
Data Index: 1423666 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.8515. Min Act: -0.1700
Data Index: 6034690 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.8203. Min Act: -0.1700
Data Index: 5268183 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.7890. Min Act: -0.1700
Data Index: 1905848 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.6953. Min Act: -0.1700
Data Index: 8525936 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.6328. Min Act: -0.1700
Data Index: 636103 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.6015. Min Act: -0.1700
Data Index: 1135999 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.5390. Min Act: -0.1700
Data Index: 5295283 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.5703. Min Act: -0.1700
Data Index: 1626667 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.4765. Min Act: -0.1700
Data Index: 8548878 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.4140. Min Act: -0.1700
Data Index: 4032125 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.4140. Min Act: -0.1700
Data Index: 6653026 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.4453. Min Act: -0.1700
Data Index: 6537831 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.4140. Min Act: -0.1700
Data Index: 7627409 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.4140. Min Act: -0.1700
Data Index: 3805683 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.4140. Min Act: -0.1700
Data Index: 8015873 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.3828. Min Act: -0.1700
Data Index: 7078446 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.3828. Min Act: -0.1700
Data Index: 2111496 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1640. Min Range: -7.1640
Max Act: 6.3515. Min Act: -0.1700
Data Index: 1927818 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19