Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1780 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7890. Min Act: -0.1700
Data Index: 6829833 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7890. Min Act: -0.1700
Data Index: 4530670 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7890. Min Act: -0.1700
Data Index: 4100380 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7578. Min Act: -0.1700
Data Index: 3770595 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7578. Min Act: -0.1700
Data Index: 7274558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7578. Min Act: -0.1700
Data Index: 3771775 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7578. Min Act: -0.1700
Data Index: 197196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7265. Min Act: -0.1700
Data Index: 1287530 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7265. Min Act: -0.1700
Data Index: 3753484 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 3098503 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 1656688 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 2902374 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 4316077 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 62923 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 4052563 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 2393685 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 3916702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 2341482 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.7265. Min Act: -0.1700
Data Index: 2298572 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7890. Min Range: -4.7890
Max Act: 4.6953. Min Act: -0.1700
Data Index: 1374036 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19