Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.7246. Min Act: -0.1700
Data Index: 1555674 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.6308. Min Act: -0.1700
Data Index: 8374030 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.4433. Min Act: -0.1700
Data Index: 6456617 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.3496. Min Act: -0.1700
Data Index: 6869899 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.2558. Min Act: -0.1700
Data Index: 1781877 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.2246. Min Act: -0.1700
Data Index: 6186446 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.1621. Min Act: -0.1700
Data Index: 2140558 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.1621. Min Act: -0.1700
Data Index: 8806810 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.1308. Min Act: -0.1700
Data Index: 7366849 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.0996. Min Act: -0.1700
Data Index: 5834938 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.0996. Min Act: -0.1700
Data Index: 3841942 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.0996. Min Act: -0.1700
Data Index: 4649668 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.0683. Min Act: -0.1700
Data Index: 3847267 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.0371. Min Act: -0.1700
Data Index: 2544644 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.0371. Min Act: -0.1700
Data Index: 8686489 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.0371. Min Act: -0.1700
Data Index: 2257863 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7246. Min Range: -7.7246
Max Act: 7.0058. Min Act: -0.1700
Data Index: 7199398 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7246. Min Range: -7.7246
Max Act: 6.9746. Min Act: -0.1700
Data Index: 3726564 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7246. Min Range: -7.7246
Max Act: 6.9433. Min Act: -0.1700
Data Index: 8424251 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7246. Min Range: -7.7246
Max Act: 6.9433. Min Act: -0.1700
Data Index: 4218329 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19