Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 565 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.9761. Min Act: -0.1700
Data Index: 6967684 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.9449. Min Act: -0.1700
Data Index: 26811 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.9449. Min Act: -0.1700
Data Index: 6741578 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.9136. Min Act: -0.1700
Data Index: 1248555 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.9136. Min Act: -0.1700
Data Index: 7931968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8511. Min Act: -0.1700
Data Index: 1846769 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8824. Min Act: -0.1699
Data Index: 4980785 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8824. Min Act: -0.1700
Data Index: 3284039 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8824. Min Act: -0.1697
Data Index: 3340383 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8824. Min Act: -0.1700
Data Index: 5947503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8824. Min Act: -0.1700
Data Index: 2639465 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8824. Min Act: -0.1700
Data Index: 7770719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8511. Min Act: -0.1700
Data Index: 5281542 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8511. Min Act: -0.1699
Data Index: 5373298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8511. Min Act: -0.1700
Data Index: 6028995 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8511. Min Act: -0.1698
Data Index: 1939297 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8511. Min Act: -0.1700
Data Index: 16082 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8511. Min Act: -0.1700
Data Index: 7617740 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8511. Min Act: -0.1700
Data Index: 4212156 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9761. Min Range: -4.9761
Max Act: 4.8199. Min Act: -0.1700
Data Index: 1069190 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19