Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 201 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.8256. Min Act: -0.1700
Data Index: 6963788 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.7567. Min Act: -0.1700
Data Index: 8556371 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.7654. Min Act: -0.1700
Data Index: 8688877 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.7308. Min Act: -0.1700
Data Index: 7209834 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.7222. Min Act: -0.1700
Data Index: 841039 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.7135. Min Act: -0.1700
Data Index: 4409831 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.7135. Min Act: -0.1700
Data Index: 1654662 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.7135. Min Act: -0.1700
Data Index: 3708632 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6962. Min Act: -0.1700
Data Index: 3924831 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.7048. Min Act: -0.1700
Data Index: 7263314 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.7048. Min Act: -0.1700
Data Index: 807920 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6962. Min Act: -0.1700
Data Index: 1952575 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6962. Min Act: -0.1700
Data Index: 6416878 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6962. Min Act: -0.1700
Data Index: 974890 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6875. Min Act: -0.1700
Data Index: 5068930 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6875. Min Act: -0.1700
Data Index: 5644483 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6788. Min Act: -0.1700
Data Index: 5911466 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6875. Min Act: -0.1699
Data Index: 312606 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6788. Min Act: -0.1700
Data Index: 1463660 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8256. Min Range: -1.8256
Max Act: 1.6875. Min Act: -0.1700
Data Index: 6845684 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19