Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1837 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.5127. Min Act: -0.1682
Data Index: 6885399 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.5215. Min Act: -0.1695
Data Index: 3273362 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.5215. Min Act: -0.1595
Data Index: 7921680 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.5040. Min Act: -0.1578
Data Index: 3273356 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4952. Min Act: -0.1494
Data Index: 2564856 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4864. Min Act: -0.1688
Data Index: 7480184 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4864. Min Act: -0.1699
Data Index: 6661600 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4776. Min Act: -0.1668
Data Index: 462954 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4776. Min Act: -0.1683
Data Index: 121869 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4600. Min Act: -0.1676
Data Index: 7902967 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4688. Min Act: -0.1700
Data Index: 5809116 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4512. Min Act: -0.1696
Data Index: 1033776 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4512. Min Act: -0.1700
Data Index: 6560789 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4512. Min Act: -0.1700
Data Index: 2028658 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4512. Min Act: -0.1678
Data Index: 7216219 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4424. Min Act: -0.1670
Data Index: 5918000 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4512. Min Act: -0.1697
Data Index: 384715 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4512. Min Act: -0.1700
Data Index: 1762719 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4600. Min Act: -0.1691
Data Index: 38942 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5215. Min Range: -1.5215
Max Act: 1.4424. Min Act: -0.1512
Data Index: 641336 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19