Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.2474. Min Act: -0.1700
Data Index: 7741910 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.1849. Min Act: -0.1700
Data Index: 4980008 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.1849. Min Act: -0.1700
Data Index: 8421731 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.1224. Min Act: -0.1700
Data Index: 1643588 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.1849. Min Act: -0.1700
Data Index: 5819772 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.1536. Min Act: -0.1700
Data Index: 486447 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.1224. Min Act: -0.1700
Data Index: 703866 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.1224. Min Act: -0.1700
Data Index: 1785371 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0911. Min Act: -0.1700
Data Index: 34851 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0286. Min Act: -0.1700
Data Index: 3708723 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0599. Min Act: -0.1700
Data Index: 3741661 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0286. Min Act: -0.1700
Data Index: 147121 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0286. Min Act: -0.1700
Data Index: 4706759 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0286. Min Act: -0.1700
Data Index: 1162952 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0599. Min Act: -0.1700
Data Index: 5209126 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0286. Min Act: -0.1700
Data Index: 5335643 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2474. Min Range: -5.2474
Max Act: 4.9974. Min Act: -0.1700
Data Index: 116483 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0286. Min Act: -0.1700
Data Index: 6012699 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2474. Min Range: -5.2474
Max Act: 4.9974. Min Act: -0.1700
Data Index: 5131107 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2474. Min Range: -5.2474
Max Act: 5.0286. Min Act: -0.1700
Data Index: 1603807 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19