Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 429 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1191. Min Range: -7.1191
Max Act: 7.1191. Min Act: -0.1700
Data Index: 7799725 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1191. Min Range: -7.1191
Max Act: 7.0879. Min Act: -0.1700
Data Index: 1453787 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1191. Min Range: -7.1191
Max Act: 7.0566. Min Act: -0.1700
Data Index: 161893 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.9629. Min Act: -0.1700
Data Index: 3622038 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.9941. Min Act: -0.1700
Data Index: 8030157 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.9941. Min Act: -0.1700
Data Index: 6325715 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.9629. Min Act: -0.1700
Data Index: 6805245 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.8066. Min Act: -0.1700
Data Index: 8759561 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.8066. Min Act: -0.1700
Data Index: 5301144 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7754. Min Act: -0.1700
Data Index: 1148556 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7441. Min Act: -0.1700
Data Index: 5320130 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7441. Min Act: -0.1700
Data Index: 1353773 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7129. Min Act: -0.1700
Data Index: 3864370 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7441. Min Act: -0.1700
Data Index: 1858750 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7129. Min Act: -0.1700
Data Index: 3525395 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7129. Min Act: -0.1700
Data Index: 7172883 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7754. Min Act: -0.1700
Data Index: 7799613 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7129. Min Act: -0.1700
Data Index: 4617085 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.7129. Min Act: -0.1700
Data Index: 4031600 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1191. Min Range: -7.1191
Max Act: 6.5879. Min Act: -0.1700
Data Index: 6175238 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19