Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4381 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.7548. Min Act: -0.1700
Data Index: 7072088 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.6611. Min Act: -0.1700
Data Index: 5936643 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.6611. Min Act: -0.1700
Data Index: 6839390 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5986. Min Act: -0.1699
Data Index: 3960462 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5673. Min Act: -0.1700
Data Index: 8180849 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5361. Min Act: -0.1700
Data Index: 1792745 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5361. Min Act: -0.1700
Data Index: 1577113 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4111. Min Act: -0.1700
Data Index: 3587480 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3798. Min Act: -0.1700
Data Index: 3604941 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3486. Min Act: -0.1700
Data Index: 2174414 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3486. Min Act: -0.1700
Data Index: 4388989 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3486. Min Act: -0.1700
Data Index: 6913721 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3173. Min Act: -0.1700
Data Index: 8216441 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3173. Min Act: -0.1695
Data Index: 5541682 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3486. Min Act: -0.1700
Data Index: 4039569 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3173. Min Act: -0.1700
Data Index: 3785391 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.2861. Min Act: -0.1700
Data Index: 6500350 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3173. Min Act: -0.1694
Data Index: 6586062 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3173. Min Act: -0.1699
Data Index: 2436567 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.2861. Min Act: -0.1700
Data Index: 6993141 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19