Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.7056. Min Act: -0.1700
Data Index: 3235819 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.2681. Min Act: -0.1700
Data Index: 8456710 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.1744. Min Act: -0.1700
Data Index: 7503672 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.1119. Min Act: -0.1700
Data Index: 4304115 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.0494. Min Act: -0.1700
Data Index: 3452203 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.0181. Min Act: -0.1700
Data Index: 8106195 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9869. Min Act: -0.1700
Data Index: 3392824 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9869. Min Act: -0.1700
Data Index: 6510168 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9869. Min Act: -0.1700
Data Index: 6825440 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9869. Min Act: -0.1700
Data Index: 2327579 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9556. Min Act: -0.1700
Data Index: 4636732 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9556. Min Act: -0.1700
Data Index: 5520820 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9556. Min Act: -0.1700
Data Index: 1014808 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9244. Min Act: -0.1700
Data Index: 3777321 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9244. Min Act: -0.1700
Data Index: 1255883 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9244. Min Act: -0.1700
Data Index: 3173468 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.9244. Min Act: -0.1700
Data Index: 3488517 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.8931. Min Act: -0.1700
Data Index: 6291010 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.8619. Min Act: -0.1700
Data Index: 7612813 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7056. Min Range: -5.7056
Max Act: 4.8931. Min Act: -0.1700
Data Index: 2007234 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19