Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2701 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4789. Min Range: -6.4789
Max Act: 6.4789. Min Act: -0.1700
Data Index: 2868234 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4789. Min Range: -6.4789
Max Act: 6.1039. Min Act: -0.1700
Data Index: 2502397 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4789. Min Range: -6.4789
Max Act: 6.0727. Min Act: -0.1700
Data Index: 3357444 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4789. Min Range: -6.4789
Max Act: 6.0102. Min Act: -0.1700
Data Index: 4787801 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.9789. Min Act: -0.1700
Data Index: 2455729 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.9477. Min Act: -0.1700
Data Index: 2648983 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.9164. Min Act: -0.1700
Data Index: 743115 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.8227. Min Act: -0.1700
Data Index: 4380608 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.8227. Min Act: -0.1700
Data Index: 4249597 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.8227. Min Act: -0.1700
Data Index: 8497137 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.8227. Min Act: -0.1700
Data Index: 7940689 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.7914. Min Act: -0.1700
Data Index: 4490839 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.7289. Min Act: -0.1700
Data Index: 3698313 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.7602. Min Act: -0.1700
Data Index: 2706033 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6659897 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.7914. Min Act: -0.1700
Data Index: 7853701 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.7289. Min Act: -0.1700
Data Index: 8514292 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.7289. Min Act: -0.1700
Data Index: 2864019 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.7289. Min Act: -0.1700
Data Index: 4444054 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4789. Min Range: -6.4789
Max Act: 5.6977. Min Act: -0.1700
Data Index: 6187321 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19