Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.8035. Min Act: -0.1691
Data Index: 1583081 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.6160. Min Act: -0.1700
Data Index: 1762459 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.4285. Min Act: -0.1700
Data Index: 7013097 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.3660. Min Act: -0.1697
Data Index: 463556 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.3035. Min Act: -0.1700
Data Index: 7736730 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.2410. Min Act: -0.1700
Data Index: 7730293 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.1785. Min Act: -0.1700
Data Index: 1385712 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.1160. Min Act: -0.1699
Data Index: 4788734 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.1160. Min Act: -0.1700
Data Index: 1424962 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.1160. Min Act: -0.1697
Data Index: 2189837 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.1160. Min Act: -0.1700
Data Index: 8687738 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.1160. Min Act: -0.1700
Data Index: 7952567 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.1160. Min Act: -0.1700
Data Index: 4471963 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.1160. Min Act: -0.1700
Data Index: 64202 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.0535. Min Act: -0.1700
Data Index: 982066 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.0535. Min Act: -0.1699
Data Index: 671324 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.0535. Min Act: -0.1700
Data Index: 2974705 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.0535. Min Act: -0.1700
Data Index: 4372430 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.0535. Min Act: -0.1695
Data Index: 7813977 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8035. Min Range: -8.8035
Max Act: 8.0535. Min Act: -0.1700
Data Index: 7412160 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19