Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 332 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.9277. Min Act: -0.1700
Data Index: 6558814 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.9277. Min Act: -0.1700
Data Index: 4446700 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.9107. Min Act: -0.1700
Data Index: 2246394 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8936. Min Act: -0.1700
Data Index: 5689626 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8765. Min Act: -0.1700
Data Index: 2778817 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8423. Min Act: -0.1700
Data Index: 1513362 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8423. Min Act: -0.1700
Data Index: 1412270 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8251. Min Act: -0.1700
Data Index: 725939 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8080. Min Act: -0.1700
Data Index: 7935204 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8080. Min Act: -0.1700
Data Index: 8039920 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8080. Min Act: -0.1700
Data Index: 9577 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.7908. Min Act: -0.1700
Data Index: 3894831 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8080. Min Act: -0.1700
Data Index: 6802701 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.7908. Min Act: -0.1700
Data Index: 182820 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.8080. Min Act: -0.1700
Data Index: 1039360 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.7908. Min Act: -0.1698
Data Index: 1817836 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.7908. Min Act: -0.1700
Data Index: 968450 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.7908. Min Act: -0.1700
Data Index: 4312217 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.7735. Min Act: -0.1700
Data Index: 791862 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9277. Min Range: -1.9277
Max Act: 1.7908. Min Act: -0.1700
Data Index: 6403450 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19