Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 270 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.2611. Min Act: -0.1700
Data Index: 8278900 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.2923. Min Act: -0.1700
Data Index: 5158473 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1673. Min Act: -0.1700
Data Index: 5292149 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1360. Min Act: -0.1700
Data Index: 3485193 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1985. Min Act: -0.1700
Data Index: 4772876 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1360. Min Act: -0.1700
Data Index: 5930723 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1360. Min Act: -0.1700
Data Index: 6219935 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1048. Min Act: -0.1700
Data Index: 7984637 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1048. Min Act: -0.1700
Data Index: 2218006 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1048. Min Act: -0.1700
Data Index: 796023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1048. Min Act: -0.1700
Data Index: 2922233 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1048. Min Act: -0.1700
Data Index: 7482461 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.0735. Min Act: -0.1700
Data Index: 5804900 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.0423. Min Act: -0.1700
Data Index: 7175972 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.1048. Min Act: -0.1700
Data Index: 5376346 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.0423. Min Act: -0.1700
Data Index: 343791 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.0110. Min Act: -0.1700
Data Index: 2142578 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.0110. Min Act: -0.1700
Data Index: 1246264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2923. Min Range: -4.2923
Max Act: 3.9797. Min Act: -0.1700
Data Index: 1565594 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2923. Min Range: -4.2923
Max Act: 4.0423. Min Act: -0.1700
Data Index: 1256970 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19