Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 329 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1415. Min Range: -4.1415
Max Act: 4.1415. Min Act: -0.1700
Data Index: 2486334 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1415. Min Range: -4.1415
Max Act: 4.0478. Min Act: -0.1700
Data Index: 7837216 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1415. Min Range: -4.1415
Max Act: 4.0478. Min Act: -0.1700
Data Index: 3612881 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1415. Min Range: -4.1415
Max Act: 4.0165. Min Act: -0.1700
Data Index: 6537359 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9852. Min Act: -0.1700
Data Index: 5874789 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9227. Min Act: -0.1700
Data Index: 4668236 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9540. Min Act: -0.1700
Data Index: 1627000 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9540. Min Act: -0.1700
Data Index: 7805014 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9540. Min Act: -0.1700
Data Index: 5945627 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9540. Min Act: -0.1700
Data Index: 6627376 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9540. Min Act: -0.1700
Data Index: 6241892 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9227. Min Act: -0.1700
Data Index: 7666616 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9227. Min Act: -0.1700
Data Index: 8227035 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9227. Min Act: -0.1700
Data Index: 1816225 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8914. Min Act: -0.1700
Data Index: 4906676 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8914. Min Act: -0.1700
Data Index: 8533615 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8914. Min Act: -0.1700
Data Index: 6598232 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8914. Min Act: -0.1700
Data Index: 3815173 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8914. Min Act: -0.1700
Data Index: 5693314 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8602. Min Act: -0.1700
Data Index: 7532438 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19