Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4215 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6228. Min Range: -9.6228
Max Act: 9.6228. Min Act: -0.1700
Data Index: 8751853 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6228. Min Range: -9.6228
Max Act: 9.3728. Min Act: -0.1700
Data Index: 3605298 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6228. Min Range: -9.6228
Max Act: 9.3103. Min Act: -0.1700
Data Index: 3605308 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6228. Min Range: -9.6228
Max Act: 9.3103. Min Act: -0.1700
Data Index: 5387354 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6228. Min Range: -9.6228
Max Act: 9.1853. Min Act: -0.1700
Data Index: 765562 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6228. Min Range: -9.6228
Max Act: 9.0603. Min Act: -0.1700
Data Index: 5811965 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6228. Min Range: -9.6228
Max Act: 9.0603. Min Act: -0.1700
Data Index: 5443588 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6228. Min Range: -9.6228
Max Act: 9.0603. Min Act: -0.1700
Data Index: 5443600 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6228. Min Range: -9.6228
Max Act: 9.0603. Min Act: -0.1700
Data Index: 3755748 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.9353. Min Act: -0.1700
Data Index: 3984300 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.8728. Min Act: -0.1700
Data Index: 8653815 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.8728. Min Act: -0.1700
Data Index: 4274901 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.8103. Min Act: -0.1700
Data Index: 5240923 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.8103. Min Act: -0.1700
Data Index: 5326622 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.8103. Min Act: -0.1700
Data Index: 91042 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.7478. Min Act: -0.1700
Data Index: 5839558 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.6853. Min Act: -0.1700
Data Index: 4029661 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.6853. Min Act: -0.1700
Data Index: 7918757 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.6853. Min Act: -0.1700
Data Index: 3480380 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6228. Min Range: -9.6228
Max Act: 8.6853. Min Act: -0.1700
Data Index: 2969841 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19