Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1550 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0378. Min Range: -5.0378
Max Act: 5.0378. Min Act: -0.1700
Data Index: 2580856 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.9753. Min Act: -0.1700
Data Index: 890108 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0378. Min Range: -5.0378
Max Act: 5.0378. Min Act: -0.1700
Data Index: 8272526 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.9128. Min Act: -0.1700
Data Index: 4121032 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.9128. Min Act: -0.1700
Data Index: 3055260 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8503. Min Act: -0.1700
Data Index: 6158934 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8816. Min Act: -0.1700
Data Index: 7470003 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8816. Min Act: -0.1700
Data Index: 2811232 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8816. Min Act: -0.1700
Data Index: 402559 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8503. Min Act: -0.1700
Data Index: 6433539 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8191. Min Act: -0.1700
Data Index: 7773737 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.7878. Min Act: -0.1700
Data Index: 652972 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8191. Min Act: -0.1700
Data Index: 8530620 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8191. Min Act: -0.1700
Data Index: 4215544 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8191. Min Act: -0.1700
Data Index: 5199217 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8191. Min Act: -0.1700
Data Index: 6371736 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8191. Min Act: -0.1700
Data Index: 6321789 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.7566. Min Act: -0.1700
Data Index: 4032874 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.7878. Min Act: -0.1700
Data Index: 8696287 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0378. Min Range: -5.0378
Max Act: 4.8191. Min Act: -0.1700
Data Index: 7706470 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19