Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.5339. Min Act: -0.1700
Data Index: 4663725 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.4714. Min Act: -0.1700
Data Index: 3091651 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.3152. Min Act: -0.1700
Data Index: 6133027 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2839. Min Act: -0.1700
Data Index: 4514626 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2526. Min Act: -0.1700
Data Index: 3952862 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2839. Min Act: -0.1700
Data Index: 158015 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2839. Min Act: -0.1700
Data Index: 1576441 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2526. Min Act: -0.1700
Data Index: 4808947 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2526. Min Act: -0.1700
Data Index: 2090559 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2839. Min Act: -0.1700
Data Index: 3462109 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2526. Min Act: -0.1700
Data Index: 959214 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2526. Min Act: -0.1700
Data Index: 1809672 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.1901. Min Act: -0.1700
Data Index: 3302347 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2526. Min Act: -0.1700
Data Index: 1158134 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2214. Min Act: -0.1700
Data Index: 6528428 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2214. Min Act: -0.1700
Data Index: 4511265 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.1901. Min Act: -0.1700
Data Index: 5461877 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2214. Min Act: -0.1700
Data Index: 5437869 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2214. Min Act: -0.1700
Data Index: 2448655 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5339. Min Range: -4.5339
Max Act: 4.2214. Min Act: -0.1700
Data Index: 4822730 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19