Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.8789. Min Act: -0.1700
Data Index: 2666989 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.6601. Min Act: -0.1700
Data Index: 2943432 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.6289. Min Act: -0.1700
Data Index: 4183132 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.5664. Min Act: -0.1700
Data Index: 4913353 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.4101. Min Act: -0.1700
Data Index: 2517042 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.3789. Min Act: -0.1700
Data Index: 2621492 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.3789. Min Act: -0.1700
Data Index: 2593552 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.3476. Min Act: -0.1700
Data Index: 3805990 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.3476. Min Act: -0.1700
Data Index: 585724 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.3476. Min Act: -0.1700
Data Index: 6963011 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.3164. Min Act: -0.1700
Data Index: 3713830 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.2539. Min Act: -0.1700
Data Index: 769788 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.2851. Min Act: -0.1700
Data Index: 6272366 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.2226. Min Act: -0.1700
Data Index: 5000636 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.2226. Min Act: -0.1700
Data Index: 247008 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.1914. Min Act: -0.1700
Data Index: 317040 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.1914. Min Act: -0.1700
Data Index: 8049748 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.1601. Min Act: -0.1700
Data Index: 8154431 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.1289. Min Act: -0.1700
Data Index: 290186 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8789. Min Range: -5.8789
Max Act: 5.1601. Min Act: -0.1700
Data Index: 4354675 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19