Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5766. Min Act: -0.1700
Data Index: 8031203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5766. Min Act: -0.1700
Data Index: 4403814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5453. Min Act: -0.1700
Data Index: 7870789 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5453. Min Act: -0.1700
Data Index: 1162993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5453. Min Act: -0.1700
Data Index: 3757560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5140. Min Act: -0.1700
Data Index: 2303546 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5453. Min Act: -0.1700
Data Index: 6307902 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5140. Min Act: -0.1700
Data Index: 5271864 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5140. Min Act: -0.1700
Data Index: 7905128 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.5140. Min Act: -0.1700
Data Index: 77779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 3831889 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 738017 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 2028953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 4035633 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 1871285 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 780946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 4853426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 2088454 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 5730957 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5766. Min Range: -3.5766
Max Act: 3.4827. Min Act: -0.1700
Data Index: 2092905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19