Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 988 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0732. Min Range: -3.0732
Max Act: 3.0732. Min Act: -0.1700
Data Index: 1942088 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0732. Min Range: -3.0732
Max Act: 3.0575. Min Act: -0.1700
Data Index: 649407 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0732. Min Range: -3.0732
Max Act: 3.0575. Min Act: -0.1700
Data Index: 1040002 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0732. Min Range: -3.0732
Max Act: 3.0575. Min Act: -0.1700
Data Index: 6296800 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0732. Min Range: -3.0732
Max Act: 3.0417. Min Act: -0.1700
Data Index: 4250575 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0732. Min Range: -3.0732
Max Act: 3.0101. Min Act: -0.1700
Data Index: 4154971 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9943. Min Act: -0.1700
Data Index: 6205024 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9943. Min Act: -0.1700
Data Index: 5309249 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9943. Min Act: -0.1700
Data Index: 1662617 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9943. Min Act: -0.1700
Data Index: 4765337 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9785. Min Act: -0.1700
Data Index: 1720108 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9785. Min Act: -0.1700
Data Index: 1296395 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9785. Min Act: -0.1700
Data Index: 1574905 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9785. Min Act: -0.1700
Data Index: 7955129 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9785. Min Act: -0.1700
Data Index: 5919339 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9785. Min Act: -0.1700
Data Index: 8328036 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9627. Min Act: -0.1700
Data Index: 2659912 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9785. Min Act: -0.1700
Data Index: 7951036 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9627. Min Act: -0.1700
Data Index: 4509305 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0732. Min Range: -3.0732
Max Act: 2.9627. Min Act: -0.1700
Data Index: 2809362 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19