Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1867 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.7138. Min Act: -0.1699
Data Index: 7758517 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6975. Min Act: -0.1693
Data Index: 2997749 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6894. Min Act: -0.1680
Data Index: 1144869 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6812. Min Act: -0.1700
Data Index: 6689767 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6651. Min Act: -0.1699
Data Index: 2997748 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6651. Min Act: -0.1700
Data Index: 2997746 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6570. Min Act: -0.1700
Data Index: 2997744 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6570. Min Act: -0.1700
Data Index: 1054034 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6570. Min Act: -0.1671
Data Index: 2997750 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6490. Min Act: -0.1700
Data Index: 3817206 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6490. Min Act: -0.1700
Data Index: 2997751 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6330. Min Act: -0.1700
Data Index: 2997745 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6410. Min Act: -0.1698
Data Index: 632841 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6330. Min Act: -0.1660
Data Index: 1402365 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6330. Min Act: -0.1696
Data Index: 4718673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6250. Min Act: -0.1691
Data Index: 5046420 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6171. Min Act: -0.1694
Data Index: 1117164 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6250. Min Act: -0.1697
Data Index: 3742578 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6250. Min Act: -0.1700
Data Index: 928912 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7138. Min Range: -0.7138
Max Act: 0.6171. Min Act: -0.1700
Data Index: 3424802 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19