Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3894 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.8740. Min Act: -0.1700
Data Index: 8584559 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.7177. Min Act: -0.1700
Data Index: 2467092 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.7177. Min Act: -0.1700
Data Index: 685971 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.7177. Min Act: -0.1700
Data Index: 6021944 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.6865. Min Act: -0.1700
Data Index: 5782460 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.7177. Min Act: -0.1700
Data Index: 1493338 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.6865. Min Act: -0.1700
Data Index: 7152971 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.7177. Min Act: -0.1700
Data Index: 5359617 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.6552. Min Act: -0.1700
Data Index: 5737695 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.5927. Min Act: -0.1700
Data Index: 7757416 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.6552. Min Act: -0.1700
Data Index: 5782853 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.6552. Min Act: -0.1700
Data Index: 5807263 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.5927. Min Act: -0.1700
Data Index: 1845487 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.5927. Min Act: -0.1700
Data Index: 1894561 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.5927. Min Act: -0.1700
Data Index: 5189386 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.6240. Min Act: -0.1700
Data Index: 7816933 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.5615. Min Act: -0.1700
Data Index: 1008915 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.5927. Min Act: -0.1700
Data Index: 7354321 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.5927. Min Act: -0.1700
Data Index: 8230303 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8740. Min Range: -5.8740
Max Act: 5.5927. Min Act: -0.1700
Data Index: 587966 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19