Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2213. Min Range: -6.2213
Max Act: 6.2213. Min Act: -0.1700
Data Index: 5504033 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2213. Min Range: -6.2213
Max Act: 6.0963. Min Act: -0.1700
Data Index: 5206663 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2213. Min Range: -6.2213
Max Act: 6.0025. Min Act: -0.1700
Data Index: 2852799 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.9713. Min Act: -0.1700
Data Index: 5755729 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.9713. Min Act: -0.1700
Data Index: 6984098 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.9400. Min Act: -0.1700
Data Index: 6212865 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.8775. Min Act: -0.1700
Data Index: 5796121 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.8775. Min Act: -0.1700
Data Index: 759429 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.8463. Min Act: -0.1700
Data Index: 7379420 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.8463. Min Act: -0.1700
Data Index: 7005099 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.8150. Min Act: -0.1700
Data Index: 3887883 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.7838. Min Act: -0.1700
Data Index: 661555 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.7838. Min Act: -0.1700
Data Index: 2053440 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.8150. Min Act: -0.1700
Data Index: 7494918 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.7525. Min Act: -0.1700
Data Index: 4267720 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.7525. Min Act: -0.1700
Data Index: 2751676 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.7525. Min Act: -0.1700
Data Index: 3808532 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.7525. Min Act: -0.1700
Data Index: 8452196 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.7213. Min Act: -0.1700
Data Index: 1499710 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2213. Min Range: -6.2213
Max Act: 5.7213. Min Act: -0.1700
Data Index: 4507052 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19