Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.8018. Min Act: -0.1609
Data Index: 1799199 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.8018. Min Act: -0.1699
Data Index: 809892 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.7393. Min Act: -0.1693
Data Index: 8633348 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.6768. Min Act: -0.1699
Data Index: 7993645 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.6455. Min Act: -0.1492
Data Index: 47426 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.6143. Min Act: -0.1700
Data Index: 3712920 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.5518. Min Act: -0.1698
Data Index: 1256570 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.5205. Min Act: -0.1459
Data Index: 807001 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.4580. Min Act: -0.1648
Data Index: 6906584 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3643. Min Act: -0.1700
Data Index: 809893 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3955. Min Act: -0.1696
Data Index: 8602728 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3643. Min Act: -0.1684
Data Index: 6388581 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3643. Min Act: -0.0511
Data Index: 1256569 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3330. Min Act: -0.1697
Data Index: 1256566 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3330. Min Act: -0.1700
Data Index: 8365431 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3018. Min Act: -0.1672
Data Index: 807002 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.2705. Min Act: -0.1689
Data Index: 1799200 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3330. Min Act: -0.1685
Data Index: 7993647 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3018. Min Act: -0.1700
Data Index: 8673659 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8018. Min Range: -6.8018
Max Act: 6.3018. Min Act: -0.1700
Data Index: 7993653 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19