Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4740 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.9048. Min Act: -0.1700
Data Index: 7386454 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.9048. Min Act: -0.1700
Data Index: 3313422 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.7798. Min Act: -0.1700
Data Index: 1927188 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.7173. Min Act: -0.1700
Data Index: 8447578 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.7173. Min Act: -0.1700
Data Index: 6230544 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.6861. Min Act: -0.1700
Data Index: 5749430 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.6548. Min Act: -0.1700
Data Index: 7779208 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.6548. Min Act: -0.1700
Data Index: 8447577 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.6236. Min Act: -0.1700
Data Index: 4452018 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.5923. Min Act: -0.1700
Data Index: 7093306 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.5923. Min Act: -0.1700
Data Index: 7661660 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.5923. Min Act: -0.1700
Data Index: 2441632 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.5611. Min Act: -0.1700
Data Index: 378436 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.5611. Min Act: -0.1700
Data Index: 8651803 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.5611. Min Act: -0.1700
Data Index: 8796269 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.4986. Min Act: -0.1700
Data Index: 5431063 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.4986. Min Act: -0.1700
Data Index: 4271276 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.4986. Min Act: -0.1700
Data Index: 2632565 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.4986. Min Act: -0.1700
Data Index: 4333245 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9048. Min Range: -4.9048
Max Act: 4.4986. Min Act: -0.1700
Data Index: 3877687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19