Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 175 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3405. Min Act: -0.1700
Data Index: 7561621 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3092. Min Act: -0.1700
Data Index: 4509345 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3092. Min Act: -0.1700
Data Index: 3402504 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 191309 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0905. Min Act: -0.1700
Data Index: 4006990 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0592. Min Act: -0.1700
Data Index: 5860509 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0592. Min Act: -0.1700
Data Index: 7245486 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0279. Min Act: -0.1700
Data Index: 1795844 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0279. Min Act: -0.1700
Data Index: 4937461 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0279. Min Act: -0.1700
Data Index: 5997237 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0279. Min Act: -0.1700
Data Index: 4582345 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3405. Min Range: -4.3405
Max Act: 3.9654. Min Act: -0.1700
Data Index: 1887524 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3405. Min Range: -4.3405
Max Act: 3.9654. Min Act: -0.1700
Data Index: 1510600 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3405. Min Range: -4.3405
Max Act: 3.9342. Min Act: -0.1700
Data Index: 2814979 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3405. Min Range: -4.3405
Max Act: 3.9654. Min Act: -0.1700
Data Index: 930432 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3405. Min Range: -4.3405
Max Act: 3.9342. Min Act: -0.1700
Data Index: 7655412 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3405. Min Range: -4.3405
Max Act: 3.9029. Min Act: -0.1700
Data Index: 2887506 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3405. Min Range: -4.3405
Max Act: 3.9029. Min Act: -0.1700
Data Index: 5652413 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3405. Min Range: -4.3405
Max Act: 3.9029. Min Act: -0.1700
Data Index: 1437371 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3405. Min Range: -4.3405
Max Act: 3.9029. Min Act: -0.1700
Data Index: 666040 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19