Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.5514. Min Act: -0.1700
Data Index: 3219376 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.3951. Min Act: -0.1700
Data Index: 2637275 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.3014. Min Act: -0.1700
Data Index: 3133941 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.2389. Min Act: -0.1700
Data Index: 1246627 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.1451. Min Act: -0.1700
Data Index: 3133942 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.1139. Min Act: -0.1700
Data Index: 16393 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.0826. Min Act: -0.1700
Data Index: 973871 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.0826. Min Act: -0.1700
Data Index: 2813242 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.0514. Min Act: -0.1700
Data Index: 1169121 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9889. Min Act: -0.1700
Data Index: 3561420 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9889. Min Act: -0.1700
Data Index: 2355225 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5514. Min Range: -5.5514
Max Act: 5.0201. Min Act: -0.1700
Data Index: 3904510 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9889. Min Act: -0.1700
Data Index: 6911613 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9889. Min Act: -0.1700
Data Index: 7636254 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9576. Min Act: -0.1700
Data Index: 5864875 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9576. Min Act: -0.1700
Data Index: 5218078 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9264. Min Act: -0.1700
Data Index: 5038640 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9576. Min Act: -0.1700
Data Index: 7495299 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9264. Min Act: -0.1700
Data Index: 3766795 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5514. Min Range: -5.5514
Max Act: 4.9264. Min Act: -0.1700
Data Index: 5890898 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19