Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1554 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.8536. Min Act: -0.1700
Data Index: 547947 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.8282. Min Act: -0.1700
Data Index: 4631618 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.8282. Min Act: -0.1700
Data Index: 7950 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.8282. Min Act: -0.1700
Data Index: 5065915 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7946. Min Act: -0.1700
Data Index: 4354024 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7779. Min Act: -0.1700
Data Index: 6934999 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7946. Min Act: -0.1700
Data Index: 7074934 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7529. Min Act: -0.1700
Data Index: 4804880 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7612. Min Act: -0.1700
Data Index: 3527581 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7612. Min Act: -0.1700
Data Index: 8310627 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7529. Min Act: -0.1700
Data Index: 4692396 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7612. Min Act: -0.1700
Data Index: 185788 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7446. Min Act: -0.1700
Data Index: 55401 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7446. Min Act: -0.1700
Data Index: 1619494 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7364. Min Act: -0.1700
Data Index: 8362674 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7446. Min Act: -0.1700
Data Index: 2431320 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7446. Min Act: -0.1700
Data Index: 4354014 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7364. Min Act: -0.1700
Data Index: 1125399 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7199. Min Act: -0.1700
Data Index: 6502795 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8536. Min Range: -0.8536
Max Act: 0.7281. Min Act: -0.1700
Data Index: 217650 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19