Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1657 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.6127. Min Act: -0.1700
Data Index: 5567703 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.3002. Min Act: -0.1700
Data Index: 490684 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.3002. Min Act: -0.1700
Data Index: 3852640 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.2377. Min Act: -0.1700
Data Index: 2458776 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.1752. Min Act: -0.1700
Data Index: 783918 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.1752. Min Act: -0.1700
Data Index: 2207461 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.1439. Min Act: -0.1700
Data Index: 4615590 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.1752. Min Act: -0.1700
Data Index: 5998721 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.1752. Min Act: -0.1700
Data Index: 1176509 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.1127. Min Act: -0.1700
Data Index: 3066293 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.1127. Min Act: -0.1700
Data Index: 4361068 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.0814. Min Act: -0.1700
Data Index: 4018946 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.0502. Min Act: -0.1700
Data Index: 2866606 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.0814. Min Act: -0.1700
Data Index: 6918661 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.0502. Min Act: -0.1700
Data Index: 566471 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.0189. Min Act: -0.1700
Data Index: 1268064 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6127. Min Range: -5.6127
Max Act: 4.9877. Min Act: -0.1700
Data Index: 5905399 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6127. Min Range: -5.6127
Max Act: 5.0189. Min Act: -0.1700
Data Index: 8771563 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6127. Min Range: -5.6127
Max Act: 4.9877. Min Act: -0.1700
Data Index: 130042 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6127. Min Range: -5.6127
Max Act: 4.9877. Min Act: -0.1700
Data Index: 1260433 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19