Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5386 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.8446. Min Act: -0.1700
Data Index: 5612566 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.5321. Min Act: -0.1700
Data Index: 5021621 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.5009. Min Act: -0.1700
Data Index: 4342616 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.4696. Min Act: -0.1700
Data Index: 8574345 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.4384. Min Act: -0.1700
Data Index: 5142395 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.3759. Min Act: -0.1700
Data Index: 6389516 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.3446. Min Act: -0.1700
Data Index: 8659460 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.3446. Min Act: -0.1700
Data Index: 7939192 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.3134. Min Act: -0.1700
Data Index: 5691383 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.3134. Min Act: -0.1700
Data Index: 3226692 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.3134. Min Act: -0.1700
Data Index: 7497274 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.2821. Min Act: -0.1700
Data Index: 7457501 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.2821. Min Act: -0.1700
Data Index: 6310674 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.2196. Min Act: -0.1700
Data Index: 504292 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.2509. Min Act: -0.1700
Data Index: 1296122 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.2196. Min Act: -0.1700
Data Index: 517693 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.2196. Min Act: -0.1700
Data Index: 186867 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.2196. Min Act: -0.1700
Data Index: 7672909 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.2196. Min Act: -0.1700
Data Index: 7554056 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8446. Min Range: -5.8446
Max Act: 5.2196. Min Act: -0.1700
Data Index: 6821791 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19