Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6291 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0086. Min Range: -6.0086
Max Act: 6.0086. Min Act: -0.1700
Data Index: 4775200 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.6336. Min Act: -0.1700
Data Index: 929860 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.5086. Min Act: -0.1700
Data Index: 728678 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.5086. Min Act: -0.1700
Data Index: 3186101 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.4774. Min Act: -0.1700
Data Index: 4404764 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.4461. Min Act: -0.1700
Data Index: 3585462 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.4461. Min Act: -0.1700
Data Index: 7370604 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.4149. Min Act: -0.1700
Data Index: 6488940 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.4149. Min Act: -0.1700
Data Index: 5034625 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.3524. Min Act: -0.1700
Data Index: 5966556 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.3836. Min Act: -0.1700
Data Index: 1922587 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.3211. Min Act: -0.1700
Data Index: 1926734 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.3524. Min Act: -0.1700
Data Index: 700073 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.2899. Min Act: -0.1700
Data Index: 7252739 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.2899. Min Act: -0.1700
Data Index: 4995729 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.2899. Min Act: -0.1700
Data Index: 3025728 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.2274. Min Act: -0.1700
Data Index: 3999500 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.2586. Min Act: -0.1700
Data Index: 3549749 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.2586. Min Act: -0.1700
Data Index: 2793206 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0086. Min Range: -6.0086
Max Act: 5.2586. Min Act: -0.1700
Data Index: 3694290 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19