Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1473 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7785. Min Act: -0.1700
Data Index: 5820258 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7868. Min Act: -0.1700
Data Index: 6829670 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7701. Min Act: -0.1700
Data Index: 954681 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7618. Min Act: -0.1700
Data Index: 4717404 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7701. Min Act: -0.1700
Data Index: 1581461 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7535. Min Act: -0.1700
Data Index: 2993381 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7618. Min Act: -0.1700
Data Index: 2069774 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7535. Min Act: -0.1700
Data Index: 8136632 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7535. Min Act: -0.1700
Data Index: 2463795 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7535. Min Act: -0.1700
Data Index: 2407359 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7535. Min Act: -0.1700
Data Index: 6969680 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7453. Min Act: -0.1700
Data Index: 1710548 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7370. Min Act: -0.1700
Data Index: 6836757 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7370. Min Act: -0.1700
Data Index: 2418186 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7453. Min Act: -0.1700
Data Index: 45461 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7370. Min Act: -0.1700
Data Index: 8631670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7370. Min Act: -0.1700
Data Index: 752130 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7370. Min Act: -0.1700
Data Index: 6281611 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7370. Min Act: -0.1700
Data Index: 6531493 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7868. Min Range: -0.7868
Max Act: 0.7288. Min Act: -0.1700
Data Index: 1489070 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19