Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 319 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.6713. Min Act: -0.1700
Data Index: 4322646 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.6016. Min Act: -0.1700
Data Index: 6793437 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5929. Min Act: -0.1700
Data Index: 4173897 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5841. Min Act: -0.1700
Data Index: 4171850 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5666. Min Act: -0.1698
Data Index: 6606557 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5666. Min Act: -0.1700
Data Index: 5601858 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5754. Min Act: -0.1699
Data Index: 5771383 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5666. Min Act: -0.1699
Data Index: 7155878 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5579. Min Act: -0.1700
Data Index: 2352455 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5579. Min Act: -0.1700
Data Index: 1395704 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5579. Min Act: -0.1695
Data Index: 4942794 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5491. Min Act: -0.1700
Data Index: 23875 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5491. Min Act: -0.1700
Data Index: 7600109 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5404. Min Act: -0.1700
Data Index: 8594252 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5404. Min Act: -0.1700
Data Index: 2551079 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5316. Min Act: -0.1691
Data Index: 5444133 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5491. Min Act: -0.1698
Data Index: 1369778 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5404. Min Act: -0.1700
Data Index: 5027854 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5316. Min Act: -0.1700
Data Index: 4670616 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6713. Min Range: -1.6713
Max Act: 1.5316. Min Act: -0.1693
Data Index: 6540460 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19