Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0211. Min Range: -5.0211
Max Act: 5.0211. Min Act: -0.1700
Data Index: 3304515 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0211. Min Range: -5.0211
Max Act: 5.0211. Min Act: -0.1700
Data Index: 5535338 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0211. Min Range: -5.0211
Max Act: 5.0211. Min Act: -0.1700
Data Index: 3920776 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.9899. Min Act: -0.1700
Data Index: 5056579 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.9899. Min Act: -0.1700
Data Index: 5414972 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.9586. Min Act: -0.1700
Data Index: 253337 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.9899. Min Act: -0.1700
Data Index: 3850027 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.9899. Min Act: -0.1700
Data Index: 579517 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.9274. Min Act: -0.1700
Data Index: 4433085 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8961. Min Act: -0.1700
Data Index: 4532311 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 8693137 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 8045104 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8961. Min Act: -0.1700
Data Index: 6603785 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8961. Min Act: -0.1700
Data Index: 1945328 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8961. Min Act: -0.1700
Data Index: 5639071 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 1467604 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 5988450 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 3190048 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 107061 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8336. Min Act: -0.1700
Data Index: 772653 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19