Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0013. Min Range: -3.0013
Max Act: 3.0013. Min Act: -0.1700
Data Index: 6168421 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9696. Min Act: -0.1700
Data Index: 3511141 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9380. Min Act: -0.1700
Data Index: 6785032 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9538. Min Act: -0.1700
Data Index: 81734 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0013. Min Range: -3.0013
Max Act: 3.0013. Min Act: -0.1700
Data Index: 3500017 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9380. Min Act: -0.1700
Data Index: 1701015 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9538. Min Act: -0.1700
Data Index: 2746762 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9380. Min Act: -0.1700
Data Index: 994649 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9380. Min Act: -0.1700
Data Index: 6021957 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9221. Min Act: -0.1700
Data Index: 2866318 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9538. Min Act: -0.1700
Data Index: 4766605 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9380. Min Act: -0.1700
Data Index: 8681373 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9538. Min Act: -0.1700
Data Index: 2746760 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.8904. Min Act: -0.1700
Data Index: 2293633 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.8904. Min Act: -0.1700
Data Index: 7923100 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.8904. Min Act: -0.1700
Data Index: 173983 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.9063. Min Act: -0.1700
Data Index: 7555027 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.8904. Min Act: -0.1700
Data Index: 1277844 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.8904. Min Act: -0.1700
Data Index: 5083845 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0013. Min Range: -3.0013
Max Act: 2.8904. Min Act: -0.1700
Data Index: 837573 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19