Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3152 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 1231682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1694
Data Index: 2457967 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 2425441 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 2229239 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 2024124 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 373215 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 1891085 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1694
Data Index: 1780496 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1693
Data Index: 1499679 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1699
Data Index: 1241499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 460160 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1697
Data Index: 1211986 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1699
Data Index: 56742 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1697
Data Index: 993365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 909981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 873017 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 10399 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1698
Data Index: 642570 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1693
Data Index: 596978 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0595. Min Range: -1.0595
Max Act: 1.0595. Min Act: -0.1700
Data Index: 514379 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19