Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.6851. Min Act: -0.1700
Data Index: 2222620 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.5289. Min Act: -0.1700
Data Index: 8636721 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.5601. Min Act: -0.1700
Data Index: 3057420 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.5601. Min Act: -0.1700
Data Index: 4963228 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.3101. Min Act: -0.1700
Data Index: 5807500 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.2476. Min Act: -0.1700
Data Index: 5807498 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.2164. Min Act: -0.1700
Data Index: 6413387 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.2164. Min Act: -0.1700
Data Index: 5807499 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.1851. Min Act: -0.1700
Data Index: 2886857 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.0914. Min Act: -0.1700
Data Index: 965703 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.1226. Min Act: -0.1700
Data Index: 6413397 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.1226. Min Act: -0.1700
Data Index: 5524361 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.0914. Min Act: -0.1700
Data Index: 891482 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.0914. Min Act: -0.1700
Data Index: 1615995 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.0914. Min Act: -0.1700
Data Index: 7718646 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.0914. Min Act: -0.1700
Data Index: 2443579 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.0914. Min Act: -0.1700
Data Index: 4111157 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.0914. Min Act: -0.1700
Data Index: 4527617 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.0914. Min Act: -0.1700
Data Index: 1952925 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.0601. Min Act: -0.1700
Data Index: 605660 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19