Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5292 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.9293. Min Act: -0.1700
Data Index: 542287 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.8355. Min Act: -0.1700
Data Index: 1988160 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.8355. Min Act: -0.1700
Data Index: 4061467 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.7730. Min Act: -0.1700
Data Index: 2074860 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.7418. Min Act: -0.1700
Data Index: 7375396 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.7418. Min Act: -0.1700
Data Index: 2182388 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.7418. Min Act: -0.1700
Data Index: 80951 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6793. Min Act: -0.1700
Data Index: 7515083 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6793. Min Act: -0.1700
Data Index: 5338086 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6168. Min Act: -0.1700
Data Index: 1852391 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6480. Min Act: -0.1700
Data Index: 52804 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6480. Min Act: -0.1700
Data Index: 2116251 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6168. Min Act: -0.1700
Data Index: 3949887 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6168. Min Act: -0.1700
Data Index: 8044000 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6168. Min Act: -0.1700
Data Index: 8275269 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6168. Min Act: -0.1700
Data Index: 1640036 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.6168. Min Act: -0.1700
Data Index: 466743 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.5855. Min Act: -0.1700
Data Index: 4169902 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.5855. Min Act: -0.1700
Data Index: 2521062 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9293. Min Range: -5.9293
Max Act: 5.5855. Min Act: -0.1700
Data Index: 1655061 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19