Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.8751. Min Act: -0.1700
Data Index: 2515321 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.8126. Min Act: -0.1700
Data Index: 856019 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.7813. Min Act: -0.1700
Data Index: 1073454 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.7501. Min Act: -0.1700
Data Index: 7869274 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.7188. Min Act: -0.1700
Data Index: 1257835 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.7188. Min Act: -0.1700
Data Index: 8296719 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.6563. Min Act: -0.1700
Data Index: 4831336 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.6876. Min Act: -0.1700
Data Index: 1927069 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.6876. Min Act: -0.1700
Data Index: 3143349 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5938. Min Act: -0.1700
Data Index: 53639 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.6251. Min Act: -0.1700
Data Index: 2711932 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5938. Min Act: -0.1700
Data Index: 1198652 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5626. Min Act: -0.1700
Data Index: 4815965 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5313. Min Act: -0.1700
Data Index: 577242 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5626. Min Act: -0.1700
Data Index: 1016265 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5626. Min Act: -0.1700
Data Index: 499472 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5313. Min Act: -0.1700
Data Index: 6382356 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5313. Min Act: -0.1700
Data Index: 7676341 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5001. Min Act: -0.1700
Data Index: 4512338 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8751. Min Range: -5.8751
Max Act: 5.5001. Min Act: -0.1700
Data Index: 6014794 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19