Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4536 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.5149. Min Act: -0.1694
Data Index: 1477612 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.4837. Min Act: -0.1699
Data Index: 6140845 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.4212. Min Act: -0.1108
Data Index: 2787123 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.3899. Min Act: -0.1697
Data Index: 6140840 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.3587. Min Act: -0.1665
Data Index: 4479079 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.3587. Min Act: -0.1700
Data Index: 1477596 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.3587. Min Act: -0.1686
Data Index: 1477586 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.3587. Min Act: -0.1678
Data Index: 1477611 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.3274. Min Act: -0.1521
Data Index: 1477613 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.3274. Min Act: -0.1696
Data Index: 1477597 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.3274. Min Act: -0.1700
Data Index: 4479077 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.3274. Min Act: -0.0633
Data Index: 4479085 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.2962. Min Act: -0.1696
Data Index: 1477599 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.2962. Min Act: -0.1602
Data Index: 6140835 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.2962. Min Act: -0.1498
Data Index: 2787128 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.2962. Min Act: -0.1700
Data Index: 929162 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.2649. Min Act: -0.1691
Data Index: 1477642 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.2649. Min Act: -0.1687
Data Index: 6140837 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.2649. Min Act: -0.1663
Data Index: 2787130 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5149. Min Range: -6.5149
Max Act: 6.2649. Min Act: -0.1567
Data Index: 4479076 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19