Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.3102. Min Act: -0.1700
Data Index: 3788953 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.2477. Min Act: -0.1700
Data Index: 5439881 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.1540. Min Act: -0.1700
Data Index: 4334718 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0915. Min Act: -0.1700
Data Index: 2205234 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0915. Min Act: -0.1700
Data Index: 7133073 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.1227. Min Act: -0.1700
Data Index: 2305907 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0915. Min Act: -0.1700
Data Index: 48590 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0602. Min Act: -0.1700
Data Index: 8801168 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0289. Min Act: -0.1700
Data Index: 3651285 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0289. Min Act: -0.1700
Data Index: 6397847 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9977. Min Act: -0.1700
Data Index: 8248705 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0289. Min Act: -0.1700
Data Index: 2331541 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9664. Min Act: -0.1700
Data Index: 4091441 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9977. Min Act: -0.1700
Data Index: 4762247 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9977. Min Act: -0.1700
Data Index: 4087090 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9664. Min Act: -0.1700
Data Index: 972499 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9664. Min Act: -0.1700
Data Index: 4772938 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9664. Min Act: -0.1700
Data Index: 5597773 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9664. Min Act: -0.1700
Data Index: 5911418 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9664. Min Act: -0.1700
Data Index: 6412207 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19