Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.8933. Min Act: -0.1700
Data Index: 2358165 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.7370. Min Act: -0.1700
Data Index: 4496269 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.7370. Min Act: -0.1700
Data Index: 2594218 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.7057. Min Act: -0.1700
Data Index: 111002 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6900. Min Act: -0.1700
Data Index: 6413012 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6744. Min Act: -0.1700
Data Index: 2366484 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6431. Min Act: -0.1700
Data Index: 2806011 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6587. Min Act: -0.1700
Data Index: 2400121 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6118. Min Act: -0.1700
Data Index: 7048838 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6431. Min Act: -0.1700
Data Index: 8187118 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.5962. Min Act: -0.1700
Data Index: 8182701 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6431. Min Act: -0.1700
Data Index: 7707404 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.5648. Min Act: -0.1700
Data Index: 5948135 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6275. Min Act: -0.1700
Data Index: 5919629 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6275. Min Act: -0.1700
Data Index: 5368731 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6275. Min Act: -0.1700
Data Index: 2309271 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6118. Min Act: -0.1700
Data Index: 399364 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6431. Min Act: -0.1700
Data Index: 7187820 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6275. Min Act: -0.1700
Data Index: 1001634 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8933. Min Range: -3.8933
Max Act: 3.6275. Min Act: -0.1700
Data Index: 8818788 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19