Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4079 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8898. Min Act: -0.1700
Data Index: 7093589 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.9068. Min Act: -0.1700
Data Index: 4156118 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8727. Min Act: -0.1700
Data Index: 8354449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8727. Min Act: -0.1700
Data Index: 6661955 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8556. Min Act: -0.1700
Data Index: 1953652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8556. Min Act: -0.1700
Data Index: 7095037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8213. Min Act: -0.1700
Data Index: 1869904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8213. Min Act: -0.1700
Data Index: 7571985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8213. Min Act: -0.1700
Data Index: 774024 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8213. Min Act: -0.1700
Data Index: 5275478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8213. Min Act: -0.1700
Data Index: 8777953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8213. Min Act: -0.1700
Data Index: 6032102 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8041. Min Act: -0.1700
Data Index: 5036765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8041. Min Act: -0.1700
Data Index: 3121743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8041. Min Act: -0.1700
Data Index: 4539531 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8041. Min Act: -0.1700
Data Index: 260887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8041. Min Act: -0.1700
Data Index: 4455628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7869. Min Act: -0.1700
Data Index: 643987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7869. Min Act: -0.1700
Data Index: 1389748 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7696. Min Act: -0.1700
Data Index: 706616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19