Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3902 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.6982. Min Act: -0.1700
Data Index: 5754525 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.5419. Min Act: -0.1700
Data Index: 7112446 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.4169. Min Act: -0.1700
Data Index: 8014937 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.3544. Min Act: -0.1700
Data Index: 4103299 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.2919. Min Act: -0.1700
Data Index: 831307 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.2294. Min Act: -0.1700
Data Index: 7858820 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.1982. Min Act: -0.1700
Data Index: 5518007 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.1044. Min Act: -0.1700
Data Index: 2693525 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0732. Min Act: -0.1700
Data Index: 5319001 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0732. Min Act: -0.1700
Data Index: 140652 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0419. Min Act: -0.1700
Data Index: 3318829 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0419. Min Act: -0.1700
Data Index: 7088211 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0107. Min Act: -0.1700
Data Index: 8066856 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0107. Min Act: -0.1700
Data Index: 4605118 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6982. Min Range: -5.6982
Max Act: 4.9794. Min Act: -0.1700
Data Index: 6499654 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0107. Min Act: -0.1700
Data Index: 6238920 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0107. Min Act: -0.1700
Data Index: 2200895 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0107. Min Act: -0.1700
Data Index: 3842407 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6982. Min Range: -5.6982
Max Act: 5.0107. Min Act: -0.1700
Data Index: 2551887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6982. Min Range: -5.6982
Max Act: 4.9794. Min Act: -0.1700
Data Index: 7040461 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19