Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5182 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.4497. Min Act: -0.1700
Data Index: 6343835 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.4184. Min Act: -0.1700
Data Index: 2543796 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.3559. Min Act: -0.1700
Data Index: 7247133 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.3247. Min Act: -0.1700
Data Index: 7803261 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.2622. Min Act: -0.1700
Data Index: 7772972 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.2309. Min Act: -0.1700
Data Index: 5285709 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.2622. Min Act: -0.1700
Data Index: 2277843 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.2622. Min Act: -0.1700
Data Index: 3746292 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.2309. Min Act: -0.1700
Data Index: 995492 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1997. Min Act: -0.1700
Data Index: 3176420 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.2309. Min Act: -0.1700
Data Index: 4071805 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1997. Min Act: -0.1700
Data Index: 645029 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1372. Min Act: -0.1700
Data Index: 8433638 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1684. Min Act: -0.1700
Data Index: 17905 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1684. Min Act: -0.1700
Data Index: 6767429 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1372. Min Act: -0.1700
Data Index: 2338220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1372. Min Act: -0.1700
Data Index: 1736837 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1059. Min Act: -0.1700
Data Index: 1672206 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1059. Min Act: -0.1700
Data Index: 5861790 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4497. Min Range: -6.4497
Max Act: 6.1059. Min Act: -0.1700
Data Index: 4108225 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19