Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3243. Min Range: -4.3243
Max Act: 4.3243. Min Act: -0.1700
Data Index: 5415707 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3243. Min Range: -4.3243
Max Act: 4.1680. Min Act: -0.1700
Data Index: 8173191 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3243. Min Range: -4.3243
Max Act: 4.0430. Min Act: -0.1700
Data Index: 4923217 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.9805. Min Act: -0.1700
Data Index: 2960256 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.9492. Min Act: -0.1700
Data Index: 111272 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.9492. Min Act: -0.1700
Data Index: 4996752 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.9492. Min Act: -0.1700
Data Index: 297699 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.9492. Min Act: -0.1700
Data Index: 4309754 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.9180. Min Act: -0.1700
Data Index: 7581692 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.9180. Min Act: -0.1700
Data Index: 6224344 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.9180. Min Act: -0.1700
Data Index: 731238 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.8867. Min Act: -0.1700
Data Index: 7390238 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.8554. Min Act: -0.1700
Data Index: 7061154 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.8554. Min Act: -0.1700
Data Index: 3728092 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.8242. Min Act: -0.1700
Data Index: 4296515 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.8554. Min Act: -0.1700
Data Index: 7771242 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.8554. Min Act: -0.1700
Data Index: 5546312 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.8242. Min Act: -0.1700
Data Index: 7857853 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.8242. Min Act: -0.1700
Data Index: 358377 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3243. Min Range: -4.3243
Max Act: 3.8242. Min Act: -0.1700
Data Index: 3570573 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19