Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3098. Min Range: -8.3098
Max Act: 8.3098. Min Act: -0.1700
Data Index: 293074 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3098. Min Range: -8.3098
Max Act: 8.0598. Min Act: -0.1700
Data Index: 966625 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.9973. Min Act: -0.1700
Data Index: 4086880 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.8723. Min Act: -0.1700
Data Index: 4582893 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.8098. Min Act: -0.1700
Data Index: 2671240 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.7473. Min Act: -0.1700
Data Index: 6304651 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.7473. Min Act: -0.1700
Data Index: 8618866 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.7473. Min Act: -0.1700
Data Index: 7432354 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.7473. Min Act: -0.1700
Data Index: 6892633 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.5911. Min Act: -0.1700
Data Index: 5196761 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.5911. Min Act: -0.1700
Data Index: 111879 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.5598. Min Act: -0.1700
Data Index: 8808790 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.5598. Min Act: -0.1700
Data Index: 3131710 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.4973. Min Act: -0.1700
Data Index: 2348081 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.5286. Min Act: -0.1700
Data Index: 4863217 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.4973. Min Act: -0.1700
Data Index: 808068 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.4973. Min Act: -0.1700
Data Index: 4002266 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.4973. Min Act: -0.1700
Data Index: 3977183 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.4348. Min Act: -0.1700
Data Index: 924121 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3098. Min Range: -8.3098
Max Act: 7.4348. Min Act: -0.1700
Data Index: 6849227 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19