Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1941 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.5358. Min Act: -0.1700
Data Index: 2878771 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.3170. Min Act: -0.1700
Data Index: 6153570 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.2545. Min Act: -0.1700
Data Index: 4243101 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.1920. Min Act: -0.1700
Data Index: 3977927 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.1608. Min Act: -0.1700
Data Index: 3515656 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.0983. Min Act: -0.1700
Data Index: 5366017 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.0983. Min Act: -0.1700
Data Index: 6341191 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.0983. Min Act: -0.1700
Data Index: 7402066 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.0670. Min Act: -0.1700
Data Index: 6273893 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.0358. Min Act: -0.1700
Data Index: 3900569 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5358. Min Range: -5.5358
Max Act: 4.9733. Min Act: -0.1700
Data Index: 5089045 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5358. Min Range: -5.5358
Max Act: 5.0045. Min Act: -0.1700
Data Index: 1206581 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5358. Min Range: -5.5358
Max Act: 4.9733. Min Act: -0.1700
Data Index: 7184974 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5358. Min Range: -5.5358
Max Act: 4.9733. Min Act: -0.1700
Data Index: 4632565 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5358. Min Range: -5.5358
Max Act: 4.9733. Min Act: -0.1700
Data Index: 4413032 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5358. Min Range: -5.5358
Max Act: 4.9733. Min Act: -0.1700
Data Index: 1086235 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5358. Min Range: -5.5358
Max Act: 4.9733. Min Act: -0.1700
Data Index: 1329780 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5358. Min Range: -5.5358
Max Act: 4.9420. Min Act: -0.1700
Data Index: 2376105 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5358. Min Range: -5.5358
Max Act: 4.9420. Min Act: -0.1700
Data Index: 1867494 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5358. Min Range: -5.5358
Max Act: 4.9420. Min Act: -0.1700
Data Index: 1975183 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19