Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 818 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0516. Min Range: -5.0516
Max Act: 5.0516. Min Act: -0.1700
Data Index: 3878197 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0516. Min Range: -5.0516
Max Act: 5.0203. Min Act: -0.1700
Data Index: 4308900 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9891. Min Act: -0.1700
Data Index: 2694607 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9891. Min Act: -0.1700
Data Index: 2919808 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9891. Min Act: -0.1700
Data Index: 4105033 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9578. Min Act: -0.1700
Data Index: 5065756 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9266. Min Act: -0.1700
Data Index: 4549129 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9266. Min Act: -0.1700
Data Index: 4896563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9266. Min Act: -0.1700
Data Index: 6775297 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9266. Min Act: -0.1700
Data Index: 6660590 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9266. Min Act: -0.1700
Data Index: 2450394 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 501850 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 6618702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 5967100 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 2295191 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1699
Data Index: 3804698 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 5272161 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 3140649 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 5120472 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 1478139 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19