Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3812 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7707. Min Act: -0.1700
Data Index: 7474544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7707. Min Act: -0.1700
Data Index: 392169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7707. Min Act: -0.1700
Data Index: 3010701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7387. Min Act: -0.1700
Data Index: 5904722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7387. Min Act: -0.1700
Data Index: 2587385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7068. Min Act: -0.1700
Data Index: 8035505 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7068. Min Act: -0.1700
Data Index: 7287784 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7068. Min Act: -0.1700
Data Index: 8214569 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7068. Min Act: -0.1700
Data Index: 2063112 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7068. Min Act: -0.1700
Data Index: 5718509 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.7068. Min Act: -0.1700
Data Index: 577767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.6747. Min Act: -0.1700
Data Index: 2385307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.6747. Min Act: -0.1698
Data Index: 989269 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.6427. Min Act: -0.1700
Data Index: 7018586 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.6427. Min Act: -0.1700
Data Index: 6361315 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.6427. Min Act: -0.1700
Data Index: 4688738 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.6427. Min Act: -0.1700
Data Index: 1582197 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.6427. Min Act: -0.1700
Data Index: 3025279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.6427. Min Act: -0.1700
Data Index: 7504782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7707. Min Range: -2.7707
Max Act: 2.6427. Min Act: -0.1700
Data Index: 6334103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19