Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2690 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4755. Min Range: -9.4755
Max Act: 9.4755. Min Act: -0.1700
Data Index: 5748773 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4755. Min Range: -9.4755
Max Act: 9.4130. Min Act: -0.1700
Data Index: 2629374 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4755. Min Range: -9.4755
Max Act: 9.1005. Min Act: -0.1700
Data Index: 1329860 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4755. Min Range: -9.4755
Max Act: 9.1630. Min Act: -0.1700
Data Index: 3735973 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4755. Min Range: -9.4755
Max Act: 9.0380. Min Act: -0.1700
Data Index: 6629497 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.7880. Min Act: -0.1700
Data Index: 8284902 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.7255. Min Act: -0.1700
Data Index: 4559538 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.6630. Min Act: -0.1700
Data Index: 6674774 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.6005. Min Act: -0.1700
Data Index: 7785736 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.6005. Min Act: -0.1700
Data Index: 7833325 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.5380. Min Act: -0.1700
Data Index: 3633854 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.5380. Min Act: -0.1700
Data Index: 7026247 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.5380. Min Act: -0.1700
Data Index: 418429 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.5380. Min Act: -0.1700
Data Index: 2629375 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.4755. Min Act: -0.1700
Data Index: 4206687 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.4755. Min Act: -0.1700
Data Index: 2697924 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.5380. Min Act: -0.1700
Data Index: 3624343 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.4130. Min Act: -0.1700
Data Index: 5962548 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.4130. Min Act: -0.1700
Data Index: 6090897 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4755. Min Range: -9.4755
Max Act: 8.3505. Min Act: -0.1700
Data Index: 1214666 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19