Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3989 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.9265. Min Act: -0.1700
Data Index: 8212557 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8953. Min Act: -0.1700
Data Index: 1533814 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 7514298 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 7958973 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 3211803 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 551345 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 4013834 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 7420242 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 2690739 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 4866090 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 5710049 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8640. Min Act: -0.1700
Data Index: 1126253 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8328. Min Act: -0.1700
Data Index: 2793636 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8328. Min Act: -0.1700
Data Index: 7088726 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8328. Min Act: -0.1700
Data Index: 2565948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8328. Min Act: -0.1700
Data Index: 6183721 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8328. Min Act: -0.1700
Data Index: 5538247 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8328. Min Act: -0.1700
Data Index: 4564430 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8328. Min Act: -0.1700
Data Index: 2250565 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9265. Min Range: -4.9265
Max Act: 4.8328. Min Act: -0.1700
Data Index: 4240990 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19