Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6369 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.8578. Min Act: -0.1700
Data Index: 2126147 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.6078. Min Act: -0.1700
Data Index: 4056788 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.5766. Min Act: -0.1700
Data Index: 6766169 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.5453. Min Act: -0.1700
Data Index: 6186414 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.4828. Min Act: -0.1700
Data Index: 364113 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.4828. Min Act: -0.1700
Data Index: 5665812 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.4516. Min Act: -0.1700
Data Index: 2307394 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.4203. Min Act: -0.1700
Data Index: 8412566 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.3891. Min Act: -0.1700
Data Index: 3935886 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.3891. Min Act: -0.1700
Data Index: 6613649 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.3578. Min Act: -0.1700
Data Index: 2713345 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.3578. Min Act: -0.1700
Data Index: 6214511 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.2953. Min Act: -0.1700
Data Index: 842083 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.2641. Min Act: -0.1700
Data Index: 175492 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.2953. Min Act: -0.1700
Data Index: 5704549 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.2016. Min Act: -0.1700
Data Index: 6314009 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.2328. Min Act: -0.1700
Data Index: 5600076 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.2328. Min Act: -0.1700
Data Index: 7702360 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.2016. Min Act: -0.1700
Data Index: 3326192 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8578. Min Range: -6.8578
Max Act: 6.1703. Min Act: -0.1700
Data Index: 4541610 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19