Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5908 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.7298. Min Act: -0.1700
Data Index: 3088021 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6985. Min Act: -0.1684
Data Index: 5544558 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.7298. Min Act: -0.1700
Data Index: 1842691 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.7298. Min Act: -0.1700
Data Index: 3158362 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6672. Min Act: -0.1700
Data Index: 2541636 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6672. Min Act: -0.1700
Data Index: 5165842 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6672. Min Act: -0.1699
Data Index: 485273 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6672. Min Act: -0.1700
Data Index: 890888 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6359. Min Act: -0.1672
Data Index: 2064714 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6046. Min Act: -0.1700
Data Index: 8485658 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6359. Min Act: -0.1699
Data Index: 7441388 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6359. Min Act: -0.1696
Data Index: 6376388 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6359. Min Act: -0.1638
Data Index: 5473381 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6359. Min Act: -0.1700
Data Index: 5746140 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6046. Min Act: -0.1694
Data Index: 4140727 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6046. Min Act: -0.1700
Data Index: 7203976 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6046. Min Act: -0.1654
Data Index: 4215717 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6046. Min Act: -0.1689
Data Index: 1608917 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6046. Min Act: -0.1700
Data Index: 1241895 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7298. Min Range: -3.7298
Max Act: 3.6046. Min Act: -0.1699
Data Index: 1318772 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19