Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0423. Min Range: -5.0423
Max Act: 5.0423. Min Act: -0.1700
Data Index: 1837074 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0423. Min Range: -5.0423
Max Act: 5.0111. Min Act: -0.1700
Data Index: 1675340 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.9173. Min Act: -0.1700
Data Index: 8017755 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.8548. Min Act: -0.1700
Data Index: 6745929 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.8236. Min Act: -0.1700
Data Index: 3522224 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.7923. Min Act: -0.1700
Data Index: 3669143 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.7611. Min Act: -0.1700
Data Index: 376211 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.7298. Min Act: -0.1700
Data Index: 8253582 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.7298. Min Act: -0.1700
Data Index: 5527851 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.7298. Min Act: -0.1700
Data Index: 3592435 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.7298. Min Act: -0.1700
Data Index: 1854501 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.6986. Min Act: -0.1700
Data Index: 6745926 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.6986. Min Act: -0.1700
Data Index: 1129690 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.6673. Min Act: -0.1700
Data Index: 8225735 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.6673. Min Act: -0.1700
Data Index: 4003910 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.6673. Min Act: -0.1700
Data Index: 1001391 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.6048. Min Act: -0.1700
Data Index: 6847407 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.5736. Min Act: -0.1700
Data Index: 1256067 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.6361. Min Act: -0.1700
Data Index: 7284603 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0423. Min Range: -5.0423
Max Act: 4.6048. Min Act: -0.1700
Data Index: 4053690 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19