Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3916 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.8643. Min Act: -0.1700
Data Index: 6438168 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.7393. Min Act: -0.1700
Data Index: 321805 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.7081. Min Act: -0.1700
Data Index: 8776388 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6768. Min Act: -0.1700
Data Index: 1294589 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6768. Min Act: -0.1700
Data Index: 2687724 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6768. Min Act: -0.1700
Data Index: 8253689 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6768. Min Act: -0.1700
Data Index: 1624990 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.7081. Min Act: -0.1700
Data Index: 6866344 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6768. Min Act: -0.1700
Data Index: 219590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6768. Min Act: -0.1700
Data Index: 5330473 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6456. Min Act: -0.1700
Data Index: 8474573 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6456. Min Act: -0.1700
Data Index: 6667345 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6456. Min Act: -0.1700
Data Index: 6188872 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6768. Min Act: -0.1700
Data Index: 5716265 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6768. Min Act: -0.1700
Data Index: 3736949 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6456. Min Act: -0.1700
Data Index: 2109255 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6456. Min Act: -0.1700
Data Index: 164606 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6768. Min Act: -0.1700
Data Index: 23225 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6456. Min Act: -0.1700
Data Index: 6917850 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8643. Min Range: -4.8643
Max Act: 4.6456. Min Act: -0.1700
Data Index: 5000930 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19