Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 469 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.7527. Min Act: -0.1700
Data Index: 4155749 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.3777. Min Act: -0.1700
Data Index: 8555298 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.3152. Min Act: -0.1700
Data Index: 8700757 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.2840. Min Act: -0.1700
Data Index: 1689229 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1902. Min Act: -0.1700
Data Index: 5079690 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.2215. Min Act: -0.1700
Data Index: 2377173 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.2215. Min Act: -0.1700
Data Index: 5648442 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.2215. Min Act: -0.1700
Data Index: 7388474 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1590. Min Act: -0.1700
Data Index: 1689226 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1590. Min Act: -0.1700
Data Index: 5648445 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1590. Min Act: -0.1700
Data Index: 3598032 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1277. Min Act: -0.1700
Data Index: 4705602 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1590. Min Act: -0.1700
Data Index: 728841 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1590. Min Act: -0.1700
Data Index: 6218899 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1277. Min Act: -0.1700
Data Index: 4121234 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1277. Min Act: -0.1700
Data Index: 1098910 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.0965. Min Act: -0.1700
Data Index: 5265130 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.1277. Min Act: -0.1700
Data Index: 5675734 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.0965. Min Act: -0.1700
Data Index: 4969381 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7527. Min Range: -5.7527
Max Act: 5.0965. Min Act: -0.1700
Data Index: 5985475 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19