Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.4250. Min Act: -0.1700
Data Index: 3350012 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1896. Min Act: -0.1700
Data Index: 8619399 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1738. Min Act: -0.1700
Data Index: 582882 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1424. Min Act: -0.1700
Data Index: 4715351 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1424. Min Act: -0.1700
Data Index: 8080945 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1424. Min Act: -0.1700
Data Index: 5632196 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1266. Min Act: -0.1700
Data Index: 626482 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1424. Min Act: -0.1700
Data Index: 3244604 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1266. Min Act: -0.1700
Data Index: 167867 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.0951. Min Act: -0.1700
Data Index: 3462888 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1266. Min Act: -0.1700
Data Index: 4312433 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.1109. Min Act: -0.1700
Data Index: 8441877 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.0951. Min Act: -0.1700
Data Index: 6894655 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.0320. Min Act: -0.1700
Data Index: 6776466 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.0478. Min Act: -0.1700
Data Index: 5648284 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.0004. Min Act: -0.1700
Data Index: 6375320 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.0162. Min Act: -0.1700
Data Index: 1317838 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.0004. Min Act: -0.1700
Data Index: 5748696 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.0004. Min Act: -0.1700
Data Index: 882019 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4250. Min Range: -3.4250
Max Act: 3.0004. Min Act: -0.1700
Data Index: 781614 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19