Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0664. Min Range: -6.0664
Max Act: 6.0664. Min Act: -0.1700
Data Index: 7291122 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.9414. Min Act: -0.1700
Data Index: 8314123 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.8789. Min Act: -0.1700
Data Index: 2538896 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7852. Min Act: -0.1700
Data Index: 2527180 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.8164. Min Act: -0.1700
Data Index: 3015085 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7539. Min Act: -0.1700
Data Index: 6683189 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7539. Min Act: -0.1700
Data Index: 4515938 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7227. Min Act: -0.1700
Data Index: 4988493 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7539. Min Act: -0.1700
Data Index: 1718218 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7227. Min Act: -0.1700
Data Index: 4500652 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7539. Min Act: -0.1700
Data Index: 6770767 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7227. Min Act: -0.1700
Data Index: 5559204 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.6914. Min Act: -0.1700
Data Index: 3271764 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7539. Min Act: -0.1700
Data Index: 1507724 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.6914. Min Act: -0.1700
Data Index: 6620626 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.7227. Min Act: -0.1700
Data Index: 1535576 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.6914. Min Act: -0.1700
Data Index: 2247282 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.6914. Min Act: -0.1700
Data Index: 5621324 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.6914. Min Act: -0.1700
Data Index: 5658387 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0664. Min Range: -6.0664
Max Act: 5.6914. Min Act: -0.1700
Data Index: 5817410 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19