Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 15
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: 4856614 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1415. Min Range: -4.1415
Max Act: 4.0790. Min Act: -0.1700
Data Index: 1921272 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1415. Min Range: -4.1415
Max Act: 4.0165. Min Act: -0.1700
Data Index: 4507291 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9852. Min Act: -0.1700
Data Index: 3805266 (Open Web Text)
Max Activating Token Index: 832
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: 4104858 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9540. Min Act: -0.1700
Data Index: 4303675 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9227. Min Act: -0.1700
Data Index: 843492 (Open Web Text)
Max Activating Token Index: 909
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: 5508025 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9227. Min Act: -0.1700
Data Index: 1633819 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9227. Min Act: -0.1700
Data Index: 6253142 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.9227. Min Act: -0.1700
Data Index: 2885138 (Open Web Text)
Max Activating Token Index: 494
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: 5873765 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8914. Min Act: -0.1700
Data Index: 304152 (Open Web Text)
Max Activating Token Index: 657
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: 1143210 (Open Web Text)
Max Activating Token Index: 499
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: 7612913 (Open Web Text)
Max Activating Token Index: 256
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: 6802282 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8602. Min Act: -0.1700
Data Index: 5958833 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8602. Min Act: -0.1700
Data Index: 2336573 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1415. Min Range: -4.1415
Max Act: 3.8602. Min Act: -0.1700
Data Index: 2502097 (Open Web Text)
Max Activating Token Index: 586
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: 3294208 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19