Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0532. Min Range: -6.0532
Max Act: 6.0532. Min Act: -0.1700
Data Index: 4623436 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.8344. Min Act: -0.1700
Data Index: 3800081 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.7719. Min Act: -0.1700
Data Index: 4394798 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.6782. Min Act: -0.1700
Data Index: 1161122 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.7407. Min Act: -0.1700
Data Index: 3556353 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.6782. Min Act: -0.1700
Data Index: 3793302 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.6157. Min Act: -0.1700
Data Index: 7229434 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.6469. Min Act: -0.1700
Data Index: 3635848 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.6157. Min Act: -0.1700
Data Index: 4018014 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.5844. Min Act: -0.1700
Data Index: 5354665 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.5844. Min Act: -0.1700
Data Index: 2388122 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.5844. Min Act: -0.1700
Data Index: 1341352 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.5532. Min Act: -0.1700
Data Index: 7237928 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.5219. Min Act: -0.1700
Data Index: 5728304 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.5219. Min Act: -0.1700
Data Index: 7931519 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.5219. Min Act: -0.1700
Data Index: 1139340 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.5532. Min Act: -0.1700
Data Index: 1861962 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.5219. Min Act: -0.1700
Data Index: 4995100 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.4907. Min Act: -0.1700
Data Index: 3636861 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.4907. Min Act: -0.1700
Data Index: 812698 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19