Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5917 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.9371. Min Act: -0.1700
Data Index: 4199480 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.8433. Min Act: -0.1700
Data Index: 2446164 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.8121. Min Act: -0.1700
Data Index: 4114226 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.7496. Min Act: -0.1700
Data Index: 6757889 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.6871. Min Act: -0.1700
Data Index: 6407789 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.6246. Min Act: -0.1700
Data Index: 6786386 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.5621. Min Act: -0.1700
Data Index: 3765518 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.5308. Min Act: -0.1700
Data Index: 5493446 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.4996. Min Act: -0.1700
Data Index: 242844 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.4996. Min Act: -0.1700
Data Index: 250218 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.4683. Min Act: -0.1700
Data Index: 5169777 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.4371. Min Act: -0.1700
Data Index: 3242908 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.4371. Min Act: -0.1700
Data Index: 1663046 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.4058. Min Act: -0.1700
Data Index: 5326850 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.4058. Min Act: -0.1700
Data Index: 8581228 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.4058. Min Act: -0.1700
Data Index: 5266342 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.3746. Min Act: -0.1700
Data Index: 7426382 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.3121. Min Act: -0.1700
Data Index: 1867026 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.3433. Min Act: -0.1700
Data Index: 4744909 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9371. Min Range: -6.9371
Max Act: 6.3746. Min Act: -0.1700
Data Index: 7061105 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19