Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2446 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.9104. Min Act: -0.1700
Data Index: 5864076 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.9104. Min Act: -0.1700
Data Index: 6246180 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.8479. Min Act: -0.1700
Data Index: 5132298 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.9104. Min Act: -0.1700
Data Index: 6928341 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 871284 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 6120128 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 8563213 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.8479. Min Act: -0.1700
Data Index: 2138209 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.8479. Min Act: -0.1700
Data Index: 3405146 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.8479. Min Act: -0.1700
Data Index: 6345300 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.8479. Min Act: -0.1700
Data Index: 6343743 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.8479. Min Act: -0.1700
Data Index: 5098638 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7229. Min Act: -0.1700
Data Index: 7216001 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 5864075 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 6242297 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.8479. Min Act: -0.1700
Data Index: 5848233 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 420012 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 4717120 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 6865166 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9104. Min Range: -8.9104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 2457869 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19