Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.3763. Min Act: -0.1700
Data Index: 8351273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.3763. Min Act: -0.1700
Data Index: 6974273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.3763. Min Act: -0.1700
Data Index: 3544518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.3451. Min Act: -0.1700
Data Index: 4535060 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.2513. Min Act: -0.1700
Data Index: 926984 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.2513. Min Act: -0.1700
Data Index: 8679496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.2513. Min Act: -0.1700
Data Index: 7291369 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.2201. Min Act: -0.1700
Data Index: 871011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.2201. Min Act: -0.1700
Data Index: 6262127 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.2201. Min Act: -0.1700
Data Index: 4570252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.2201. Min Act: -0.1700
Data Index: 2159992 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.2201. Min Act: -0.1700
Data Index: 5259878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.1888. Min Act: -0.1700
Data Index: 737982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.1888. Min Act: -0.1700
Data Index: 4455281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.2201. Min Act: -0.1700
Data Index: 7814972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.1888. Min Act: -0.1700
Data Index: 8147194 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.1575. Min Act: -0.1700
Data Index: 5526977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.1575. Min Act: -0.1700
Data Index: 4124856 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.1575. Min Act: -0.1700
Data Index: 4553005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3763. Min Range: -4.3763
Max Act: 4.1575. Min Act: -0.1700
Data Index: 7747410 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19