Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.3755. Min Act: -0.1700
Data Index: 3365108 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.2818. Min Act: -0.1700
Data Index: 4434390 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.2505. Min Act: -0.1700
Data Index: 437993 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.2193. Min Act: -0.1700
Data Index: 4434392 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.1255. Min Act: -0.1700
Data Index: 5207855 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.1255. Min Act: -0.1700
Data Index: 8409816 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.0943. Min Act: -0.1700
Data Index: 3963295 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.1255. Min Act: -0.1700
Data Index: 5602174 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.0630. Min Act: -0.1700
Data Index: 8008600 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.0630. Min Act: -0.1700
Data Index: 998376 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.0630. Min Act: -0.1700
Data Index: 2649376 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.0318. Min Act: -0.1700
Data Index: 236900 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.0005. Min Act: -0.1700
Data Index: 1611286 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3755. Min Range: -5.3755
Max Act: 4.9693. Min Act: -0.1700
Data Index: 4691129 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3755. Min Range: -5.3755
Max Act: 5.0005. Min Act: -0.1700
Data Index: 4957200 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3755. Min Range: -5.3755
Max Act: 4.9693. Min Act: -0.1700
Data Index: 7145217 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3755. Min Range: -5.3755
Max Act: 4.9380. Min Act: -0.1700
Data Index: 5022553 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3755. Min Range: -5.3755
Max Act: 4.9380. Min Act: -0.1700
Data Index: 4784773 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3755. Min Range: -5.3755
Max Act: 4.9068. Min Act: -0.1700
Data Index: 2624954 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3755. Min Range: -5.3755
Max Act: 4.9068. Min Act: -0.1700
Data Index: 2965582 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19