Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.5454. Min Act: -0.1700
Data Index: 1827720 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.5142. Min Act: -0.1700
Data Index: 8131757 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.3892. Min Act: -0.1700
Data Index: 2451221 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2954. Min Act: -0.1700
Data Index: 7290314 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2954. Min Act: -0.1700
Data Index: 1294521 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2954. Min Act: -0.1700
Data Index: 2657611 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.3267. Min Act: -0.1700
Data Index: 1353829 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.3267. Min Act: -0.1700
Data Index: 5470677 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2954. Min Act: -0.1700
Data Index: 1091739 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2642. Min Act: -0.1700
Data Index: 3586356 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2329. Min Act: -0.1700
Data Index: 5786929 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2017. Min Act: -0.1700
Data Index: 8800671 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2329. Min Act: -0.1700
Data Index: 7623211 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2017. Min Act: -0.1700
Data Index: 1480034 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.2017. Min Act: -0.1700
Data Index: 884075 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.1704. Min Act: -0.1700
Data Index: 1236944 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.1704. Min Act: -0.1700
Data Index: 2483077 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.1392. Min Act: -0.1700
Data Index: 6357645 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.1704. Min Act: -0.1700
Data Index: 5641730 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5454. Min Range: -5.5454
Max Act: 5.1704. Min Act: -0.1700
Data Index: 6357647 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19