Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4361 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.8047. Min Range: -9.8047
Max Act: 9.8047. Min Act: -0.1700
Data Index: 7396549 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8047. Min Range: -9.8047
Max Act: 9.7422. Min Act: -0.1700
Data Index: 7396553 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8047. Min Range: -9.8047
Max Act: 9.3047. Min Act: -0.1700
Data Index: 638341 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.8047. Min Act: -0.1700
Data Index: 7396552 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.7422. Min Act: -0.1700
Data Index: 7396554 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.8047. Min Act: -0.1700
Data Index: 7396551 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.6797. Min Act: -0.1700
Data Index: 7396542 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.6797. Min Act: -0.1700
Data Index: 5165456 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.6172. Min Act: -0.1700
Data Index: 638339 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.5547. Min Act: -0.1700
Data Index: 7396550 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.4922. Min Act: -0.1700
Data Index: 5053402 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.4922. Min Act: -0.1700
Data Index: 4821637 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.4922. Min Act: -0.1700
Data Index: 5972762 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.4297. Min Act: -0.1700
Data Index: 2573581 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.4297. Min Act: -0.1700
Data Index: 7396556 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.4297. Min Act: -0.1700
Data Index: 624242 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.3672. Min Act: -0.1700
Data Index: 554834 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.3047. Min Act: -0.1700
Data Index: 1863030 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.3359. Min Act: -0.1700
Data Index: 7396541 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8047. Min Range: -9.8047
Max Act: 8.2734. Min Act: -0.1700
Data Index: 327206 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19