Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.7391. Min Act: -0.1687
Data Index: 2975032 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.7309. Min Act: -0.1696
Data Index: 5319355 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.7063. Min Act: -0.1664
Data Index: 8521377 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6818. Min Act: -0.1693
Data Index: 4768251 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6818. Min Act: -0.1695
Data Index: 8019749 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6737. Min Act: -0.1700
Data Index: 6640437 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6657. Min Act: -0.1688
Data Index: 5285431 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6657. Min Act: -0.1698
Data Index: 4240533 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6576. Min Act: -0.1697
Data Index: 1353762 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6576. Min Act: -0.1700
Data Index: 2027919 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6576. Min Act: -0.1700
Data Index: 441526 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6576. Min Act: -0.1700
Data Index: 5828696 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6496. Min Act: -0.1700
Data Index: 4218717 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6496. Min Act: -0.1699
Data Index: 2875999 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6336. Min Act: -0.1697
Data Index: 7792585 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6336. Min Act: -0.1695
Data Index: 3911968 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6256. Min Act: -0.1700
Data Index: 1385242 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6336. Min Act: -0.1700
Data Index: 6357577 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6177. Min Act: -0.1700
Data Index: 6989132 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7391. Min Range: -0.7391
Max Act: 0.6177. Min Act: -0.1700
Data Index: 333005 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19