Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2099 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4131. Min Range: -9.4131
Max Act: 9.4131. Min Act: -0.1700
Data Index: 5288392 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4131. Min Range: -9.4131
Max Act: 9.1631. Min Act: -0.1700
Data Index: 4428836 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4131. Min Range: -9.4131
Max Act: 9.1006. Min Act: -0.1700
Data Index: 4159432 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4131. Min Range: -9.4131
Max Act: 9.0381. Min Act: -0.1700
Data Index: 6925604 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.9131. Min Act: -0.1700
Data Index: 1406413 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.8506. Min Act: -0.1700
Data Index: 8214392 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.7881. Min Act: -0.1700
Data Index: 3973579 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.7256. Min Act: -0.1700
Data Index: 6329422 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.7256. Min Act: -0.1700
Data Index: 8799173 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.7256. Min Act: -0.1700
Data Index: 6891071 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.7256. Min Act: -0.1700
Data Index: 8788824 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.6631. Min Act: -0.1700
Data Index: 8486786 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.6631. Min Act: -0.1700
Data Index: 1826341 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.6631. Min Act: -0.1700
Data Index: 5726144 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.6631. Min Act: -0.1700
Data Index: 676678 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.6006. Min Act: -0.1700
Data Index: 5298045 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.6006. Min Act: -0.1700
Data Index: 3815003 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.6006. Min Act: -0.1700
Data Index: 8442748 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.5381. Min Act: -0.1700
Data Index: 3514444 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4131. Min Range: -9.4131
Max Act: 8.5381. Min Act: -0.1700
Data Index: 197558 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19