Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4373 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2974. Min Range: -8.2974
Max Act: 8.2974. Min Act: -0.1700
Data Index: 7973973 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2974. Min Range: -8.2974
Max Act: 8.0474. Min Act: -0.1700
Data Index: 1208694 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2974. Min Range: -8.2974
Max Act: 8.0162. Min Act: -0.1700
Data Index: 3424681 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2974. Min Range: -8.2974
Max Act: 8.0474. Min Act: -0.1700
Data Index: 3651322 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.9224. Min Act: -0.1700
Data Index: 1765714 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.8912. Min Act: -0.1700
Data Index: 2323334 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.8287. Min Act: -0.1700
Data Index: 7902933 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.7974. Min Act: -0.1700
Data Index: 3611364 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.7974. Min Act: -0.1700
Data Index: 4812754 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.7662. Min Act: -0.1700
Data Index: 8831087 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.7349. Min Act: -0.1700
Data Index: 5771018 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.7037. Min Act: -0.1700
Data Index: 8631366 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.7037. Min Act: -0.1700
Data Index: 4999118 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.7037. Min Act: -0.1700
Data Index: 887394 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.6724. Min Act: -0.1700
Data Index: 1805574 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.6412. Min Act: -0.1700
Data Index: 8434011 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.6412. Min Act: -0.1700
Data Index: 2900119 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.6412. Min Act: -0.1700
Data Index: 7646256 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.6412. Min Act: -0.1700
Data Index: 1994720 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2974. Min Range: -8.2974
Max Act: 7.6099. Min Act: -0.1700
Data Index: 7894152 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19