Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5315 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.7311. Min Act: -0.1700
Data Index: 4762428 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.6686. Min Act: -0.1700
Data Index: 167830 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.6373. Min Act: -0.1700
Data Index: 2868979 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.4811. Min Act: -0.1700
Data Index: 6058714 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.2936. Min Act: -0.1700
Data Index: 4255578 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.2623. Min Act: -0.1700
Data Index: 7179018 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.2623. Min Act: -0.1700
Data Index: 1305126 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.2623. Min Act: -0.1700
Data Index: 953443 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.2311. Min Act: -0.1700
Data Index: 2581677 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.1998. Min Act: -0.1700
Data Index: 8085153 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.1998. Min Act: -0.1700
Data Index: 5707482 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.1373. Min Act: -0.1700
Data Index: 955755 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.1373. Min Act: -0.1700
Data Index: 3026921 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.1373. Min Act: -0.1700
Data Index: 5938050 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.1373. Min Act: -0.1700
Data Index: 7523141 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.1373. Min Act: -0.1700
Data Index: 7302639 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.1061. Min Act: -0.1700
Data Index: 3430612 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.0748. Min Act: -0.1700
Data Index: 4129821 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.0436. Min Act: -0.1700
Data Index: 6593321 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7311. Min Range: -6.7311
Max Act: 6.0436. Min Act: -0.1700
Data Index: 2442113 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19