Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.2517. Min Act: -0.1700
Data Index: 841045 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.1892. Min Act: -0.1700
Data Index: 1301831 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.1580. Min Act: -0.1700
Data Index: 1618650 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.1580. Min Act: -0.1700
Data Index: 8180761 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.1267. Min Act: -0.1700
Data Index: 491415 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.1267. Min Act: -0.1700
Data Index: 2116228 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.0955. Min Act: -0.1700
Data Index: 4799036 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.0329. Min Act: -0.1700
Data Index: 6657796 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.0329. Min Act: -0.1700
Data Index: 6017633 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2517. Min Range: -4.2517
Max Act: 4.0017. Min Act: -0.1700
Data Index: 6657797 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9704. Min Act: -0.1700
Data Index: 2978809 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9704. Min Act: -0.1700
Data Index: 2372039 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9704. Min Act: -0.1700
Data Index: 3638780 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9079. Min Act: -0.1700
Data Index: 4375443 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9392. Min Act: -0.1700
Data Index: 287919 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9079. Min Act: -0.1700
Data Index: 7225712 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9392. Min Act: -0.1700
Data Index: 6017637 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9392. Min Act: -0.1700
Data Index: 7534915 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9392. Min Act: -0.1700
Data Index: 2295733 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2517. Min Range: -4.2517
Max Act: 3.9392. Min Act: -0.1700
Data Index: 4998982 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19