Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2759 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2705. Min Act: -0.1700
Data Index: 7850638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2705. Min Act: -0.1700
Data Index: 8142420 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2705. Min Act: -0.1700
Data Index: 4150510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2705. Min Act: -0.1700
Data Index: 3045920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 3617904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 4372890 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 4661083 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 3993107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 3970334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 1966851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 7674700 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 1832713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 6073181 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2390. Min Act: -0.1700
Data Index: 3496658 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2076. Min Act: -0.1700
Data Index: 760572 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2076. Min Act: -0.1700
Data Index: 1918372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2076. Min Act: -0.1700
Data Index: 250582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2076. Min Act: -0.1700
Data Index: 2525736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2076. Min Act: -0.1700
Data Index: 3916005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2705. Min Range: -3.2705
Max Act: 3.2076. Min Act: -0.1700
Data Index: 6117055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19