Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1415. Min Range: -6.1415
Max Act: 6.1415. Min Act: -0.1700
Data Index: 6633955 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1415. Min Range: -6.1415
Max Act: 6.0790. Min Act: -0.1700
Data Index: 6809622 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1415. Min Range: -6.1415
Max Act: 6.0790. Min Act: -0.1700
Data Index: 2788998 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1415. Min Range: -6.1415
Max Act: 6.0165. Min Act: -0.1700
Data Index: 2380419 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1415. Min Range: -6.1415
Max Act: 6.0477. Min Act: -0.1700
Data Index: 3421236 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1415. Min Range: -6.1415
Max Act: 6.0165. Min Act: -0.1700
Data Index: 3739324 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1415. Min Range: -6.1415
Max Act: 6.0165. Min Act: -0.1700
Data Index: 397270 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1415. Min Range: -6.1415
Max Act: 6.0165. Min Act: -0.1700
Data Index: 4627858 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9852. Min Act: -0.1700
Data Index: 4140708 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9852. Min Act: -0.1700
Data Index: 6365834 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9540. Min Act: -0.1700
Data Index: 699663 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9540. Min Act: -0.1700
Data Index: 8520941 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9852. Min Act: -0.1700
Data Index: 6461797 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9227. Min Act: -0.1700
Data Index: 135413 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9227. Min Act: -0.1700
Data Index: 8628050 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9227. Min Act: -0.1700
Data Index: 4301664 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9227. Min Act: -0.1700
Data Index: 2777013 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.9227. Min Act: -0.1700
Data Index: 7412323 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.8602. Min Act: -0.1700
Data Index: 5078633 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1415. Min Range: -6.1415
Max Act: 5.8915. Min Act: -0.1700
Data Index: 545474 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19