Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.7430. Min Act: -0.1700
Data Index: 7310069 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.4930. Min Act: -0.1700
Data Index: 6188140 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.5243. Min Act: -0.1700
Data Index: 1216596 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.3993. Min Act: -0.1700
Data Index: 2524554 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.3993. Min Act: -0.1700
Data Index: 8056717 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.3680. Min Act: -0.1700
Data Index: 5290620 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.3993. Min Act: -0.1700
Data Index: 4210985 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.3368. Min Act: -0.1700
Data Index: 3845409 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.3368. Min Act: -0.1700
Data Index: 5624403 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.3055. Min Act: -0.1700
Data Index: 1239292 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.3055. Min Act: -0.1700
Data Index: 6896108 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.3055. Min Act: -0.1700
Data Index: 201746 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.2430. Min Act: -0.1700
Data Index: 930212 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.2743. Min Act: -0.1700
Data Index: 6829494 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.2743. Min Act: -0.1700
Data Index: 6304874 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.2743. Min Act: -0.1700
Data Index: 5057668 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.2430. Min Act: -0.1700
Data Index: 5057670 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.2430. Min Act: -0.1700
Data Index: 2621350 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.2430. Min Act: -0.1700
Data Index: 6953741 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7430. Min Range: -5.7430
Max Act: 5.2430. Min Act: -0.1700
Data Index: 4349100 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19