Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.5006. Min Act: -0.1700
Data Index: 4088318 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.5006. Min Act: -0.1700
Data Index: 1226898 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4682. Min Act: -0.1700
Data Index: 7934499 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4844. Min Act: -0.1700
Data Index: 6229076 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4844. Min Act: -0.1700
Data Index: 3457581 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4519. Min Act: -0.1700
Data Index: 2457137 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4357. Min Act: -0.1700
Data Index: 7580012 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4519. Min Act: -0.1700
Data Index: 4015172 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4357. Min Act: -0.1700
Data Index: 6315481 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4357. Min Act: -0.1700
Data Index: 3835022 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4194. Min Act: -0.1700
Data Index: 2475771 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4194. Min Act: -0.1700
Data Index: 4097084 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4194. Min Act: -0.1700
Data Index: 5731963 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4194. Min Act: -0.1700
Data Index: 5722825 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4357. Min Act: -0.1700
Data Index: 5649400 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4357. Min Act: -0.1700
Data Index: 1661265 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4031. Min Act: -0.1700
Data Index: 926853 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4031. Min Act: -0.1700
Data Index: 897907 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4194. Min Act: -0.1700
Data Index: 5833118 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5006. Min Range: -2.5006
Max Act: 2.4194. Min Act: -0.1700
Data Index: 5801295 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19