Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3434 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.7329. Min Act: -0.1700
Data Index: 5980402 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.7010. Min Act: -0.1700
Data Index: 6265956 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6849. Min Act: -0.1700
Data Index: 5981078 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6689. Min Act: -0.1700
Data Index: 8433845 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6529. Min Act: -0.1700
Data Index: 4068945 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6529. Min Act: -0.1700
Data Index: 3634313 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6529. Min Act: -0.1700
Data Index: 2030813 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6368. Min Act: -0.1700
Data Index: 3056751 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6208. Min Act: -0.1700
Data Index: 7177809 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6047. Min Act: -0.1700
Data Index: 7142330 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6529. Min Act: -0.1700
Data Index: 3181660 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6047. Min Act: -0.1700
Data Index: 8556924 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6047. Min Act: -0.1700
Data Index: 5360168 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.5886. Min Act: -0.1700
Data Index: 8805719 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6047. Min Act: -0.1700
Data Index: 8553932 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6047. Min Act: -0.1700
Data Index: 8324696 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.5886. Min Act: -0.1700
Data Index: 6126934 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.5886. Min Act: -0.1700
Data Index: 6755844 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.5725. Min Act: -0.1700
Data Index: 5613607 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.6047. Min Act: -0.1700
Data Index: 2030802 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19