Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3907 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.9600. Min Act: -0.1700
Data Index: 6646180 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.8037. Min Act: -0.1700
Data Index: 8695130 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.8037. Min Act: -0.1700
Data Index: 4590173 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.7100. Min Act: -0.1700
Data Index: 7527992 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.6475. Min Act: -0.1700
Data Index: 3230033 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.6475. Min Act: -0.1700
Data Index: 512536 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.6787. Min Act: -0.1700
Data Index: 6062453 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.6162. Min Act: -0.1700
Data Index: 8634106 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.5537. Min Act: -0.1700
Data Index: 6723192 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.5537. Min Act: -0.1700
Data Index: 7948110 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.5537. Min Act: -0.1700
Data Index: 2989885 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.5537. Min Act: -0.1700
Data Index: 5921298 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.5225. Min Act: -0.1700
Data Index: 5186812 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.5225. Min Act: -0.1700
Data Index: 3077395 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.4912. Min Act: -0.1700
Data Index: 3335209 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.4912. Min Act: -0.1700
Data Index: 6571758 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.4912. Min Act: -0.1700
Data Index: 2731296 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.4912. Min Act: -0.1700
Data Index: 8805468 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.4600. Min Act: -0.1700
Data Index: 7724090 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9600. Min Range: -4.9600
Max Act: 4.4912. Min Act: -0.1700
Data Index: 5009655 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19