Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5855 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.6578. Min Act: -0.1700
Data Index: 7303776 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.6578. Min Act: -0.1700
Data Index: 2490815 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.5641. Min Act: -0.1700
Data Index: 1805721 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.5328. Min Act: -0.1700
Data Index: 5313104 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.5328. Min Act: -0.1700
Data Index: 4688485 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.5328. Min Act: -0.1700
Data Index: 389122 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.5016. Min Act: -0.1700
Data Index: 8550071 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.4391. Min Act: -0.1700
Data Index: 1805726 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.4078. Min Act: -0.1700
Data Index: 5046255 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.4078. Min Act: -0.1700
Data Index: 1861702 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.4078. Min Act: -0.1700
Data Index: 5324239 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.3766. Min Act: -0.1700
Data Index: 5875422 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.3141. Min Act: -0.1700
Data Index: 4260517 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.2828. Min Act: -0.1700
Data Index: 6568088 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.2828. Min Act: -0.1700
Data Index: 6074196 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.2516. Min Act: -0.1700
Data Index: 768878 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.2203. Min Act: -0.1700
Data Index: 3020681 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.2203. Min Act: -0.1700
Data Index: 3013543 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.1891. Min Act: -0.1700
Data Index: 4419010 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.1891. Min Act: -0.1700
Data Index: 2218405 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19