Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.6317. Min Act: -0.1700
Data Index: 3927998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.6317. Min Act: -0.1700
Data Index: 415019 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.6004. Min Act: -0.1700
Data Index: 7526543 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5691. Min Act: -0.1700
Data Index: 633373 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5691. Min Act: -0.1700
Data Index: 500298 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5691. Min Act: -0.1700
Data Index: 422209 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5691. Min Act: -0.1700
Data Index: 2611577 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5691. Min Act: -0.1700
Data Index: 6867305 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5691. Min Act: -0.1700
Data Index: 6840781 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5691. Min Act: -0.1700
Data Index: 6807620 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5691. Min Act: -0.1700
Data Index: 5846892 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5378. Min Act: -0.1700
Data Index: 900886 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5691. Min Act: -0.1700
Data Index: 2180990 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5378. Min Act: -0.1700
Data Index: 1057115 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5378. Min Act: -0.1700
Data Index: 685217 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5378. Min Act: -0.1700
Data Index: 1078847 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5378. Min Act: -0.1700
Data Index: 2700553 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5378. Min Act: -0.1700
Data Index: 1174009 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5378. Min Act: -0.1700
Data Index: 2772113 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6317. Min Range: -3.6317
Max Act: 3.5378. Min Act: -0.1700
Data Index: 120578 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19