Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3075 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.5910. Min Act: -0.1700
Data Index: 4043886 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.5597. Min Act: -0.1700
Data Index: 7482750 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.2785. Min Act: -0.1700
Data Index: 612480 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.2785. Min Act: -0.1700
Data Index: 8148005 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.2472. Min Act: -0.1700
Data Index: 5136611 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.2160. Min Act: -0.1700
Data Index: 4859379 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1847. Min Act: -0.1700
Data Index: 338091 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1847. Min Act: -0.1700
Data Index: 6430482 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1847. Min Act: -0.1700
Data Index: 3988365 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1535. Min Act: -0.1700
Data Index: 4688660 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1535. Min Act: -0.1700
Data Index: 3062679 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1535. Min Act: -0.1700
Data Index: 7276723 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1535. Min Act: -0.1700
Data Index: 7325161 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1535. Min Act: -0.1700
Data Index: 1067705 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1222. Min Act: -0.1700
Data Index: 3894123 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1847. Min Act: -0.1700
Data Index: 5012670 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1222. Min Act: -0.1700
Data Index: 5727451 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1222. Min Act: -0.1700
Data Index: 8016679 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1222. Min Act: -0.1700
Data Index: 6942403 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5910. Min Range: -4.5910
Max Act: 4.1222. Min Act: -0.1700
Data Index: 1220934 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19