Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1048 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.9810. Min Act: -0.1700
Data Index: 1721091 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.9185. Min Act: -0.1698
Data Index: 6861957 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.9185. Min Act: -0.1700
Data Index: 2366800 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8872. Min Act: -0.1699
Data Index: 7875490 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8872. Min Act: -0.1700
Data Index: 734560 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8872. Min Act: -0.1700
Data Index: 1786450 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8560. Min Act: -0.1700
Data Index: 4066182 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8560. Min Act: -0.1700
Data Index: 3101908 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8560. Min Act: -0.1700
Data Index: 2874581 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8560. Min Act: -0.1700
Data Index: 4472289 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8560. Min Act: -0.1700
Data Index: 1705493 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8560. Min Act: -0.1700
Data Index: 5618931 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8247. Min Act: -0.1700
Data Index: 1456525 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8247. Min Act: -0.1698
Data Index: 1765563 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8247. Min Act: -0.1698
Data Index: 7808217 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8247. Min Act: -0.1700
Data Index: 4016990 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8247. Min Act: -0.1700
Data Index: 1613650 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8247. Min Act: -0.1700
Data Index: 8788772 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8247. Min Act: -0.1700
Data Index: 3620973 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7935. Min Act: -0.1700
Data Index: 5460382 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19