Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3849 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.8018. Min Act: -0.1700
Data Index: 7974381 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.6768. Min Act: -0.1700
Data Index: 4667297 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.6456. Min Act: -0.1700
Data Index: 507371 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.6143. Min Act: -0.1700
Data Index: 1422687 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5831. Min Act: -0.1700
Data Index: 5495887 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5206. Min Act: -0.1700
Data Index: 3820682 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5518. Min Act: -0.1700
Data Index: 4235807 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5831. Min Act: -0.1700
Data Index: 3167985 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5518. Min Act: -0.1700
Data Index: 3156242 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5206. Min Act: -0.1700
Data Index: 7459717 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5206. Min Act: -0.1700
Data Index: 3942065 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5206. Min Act: -0.1700
Data Index: 5723619 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5206. Min Act: -0.1700
Data Index: 1422686 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.4893. Min Act: -0.1700
Data Index: 4934760 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.4893. Min Act: -0.1700
Data Index: 2271066 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.5206. Min Act: -0.1700
Data Index: 7928718 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.4893. Min Act: -0.1700
Data Index: 146062 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.4893. Min Act: -0.1700
Data Index: 1609801 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.4581. Min Act: -0.1700
Data Index: 6748177 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8018. Min Range: -4.8018
Max Act: 4.4581. Min Act: -0.1700
Data Index: 7355784 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19