Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.8706. Min Act: -0.1700
Data Index: 3579940 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.5893. Min Act: -0.1700
Data Index: 3980637 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.5581. Min Act: -0.1700
Data Index: 3485390 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.5581. Min Act: -0.1700
Data Index: 3536181 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.4331. Min Act: -0.1700
Data Index: 8456520 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.4643. Min Act: -0.1700
Data Index: 404144 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.4018. Min Act: -0.1700
Data Index: 3935133 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.4018. Min Act: -0.1700
Data Index: 8284125 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.4018. Min Act: -0.1700
Data Index: 7728133 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.3393. Min Act: -0.1700
Data Index: 4184600 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.3393. Min Act: -0.1700
Data Index: 8428522 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.3081. Min Act: -0.1700
Data Index: 8523487 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.2768. Min Act: -0.1700
Data Index: 6230143 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.2456. Min Act: -0.1700
Data Index: 8194922 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.2143. Min Act: -0.1700
Data Index: 7119692 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.2143. Min Act: -0.1700
Data Index: 7922695 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.2143. Min Act: -0.1700
Data Index: 6841099 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.1831. Min Act: -0.1700
Data Index: 3145550 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.1831. Min Act: -0.1700
Data Index: 480877 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8706. Min Range: -6.8706
Max Act: 6.1831. Min Act: -0.1700
Data Index: 5091474 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19