Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3862 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.3719. Min Act: -0.1700
Data Index: 3270313 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.2156. Min Act: -0.1700
Data Index: 1045128 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.1843. Min Act: -0.1700
Data Index: 2501743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.1218. Min Act: -0.1700
Data Index: 7889456 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.1218. Min Act: -0.1700
Data Index: 2056033 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.1218. Min Act: -0.1700
Data Index: 7070222 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.1218. Min Act: -0.1700
Data Index: 6533124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.1218. Min Act: -0.1700
Data Index: 8588585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.1218. Min Act: -0.1700
Data Index: 2583088 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0593. Min Act: -0.1700
Data Index: 5778496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0593. Min Act: -0.1700
Data Index: 6748911 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0906. Min Act: -0.1700
Data Index: 6741888 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0906. Min Act: -0.1700
Data Index: 6388720 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0906. Min Act: -0.1700
Data Index: 3750903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0906. Min Act: -0.1700
Data Index: 1681846 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0906. Min Act: -0.1700
Data Index: 8109110 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0906. Min Act: -0.1700
Data Index: 3724046 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0906. Min Act: -0.1700
Data Index: 470260 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0906. Min Act: -0.1700
Data Index: 4946452 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3719. Min Range: -4.3719
Max Act: 4.0906. Min Act: -0.1700
Data Index: 4258457 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19