Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0060. Min Range: -8.0060
Max Act: 8.0060. Min Act: -0.1700
Data Index: 3070364 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.9748. Min Act: -0.1700
Data Index: 4620316 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.8810. Min Act: -0.1700
Data Index: 7660599 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.8810. Min Act: -0.1700
Data Index: 3669152 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.8185. Min Act: -0.1700
Data Index: 339408 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.6623. Min Act: -0.1700
Data Index: 2728975 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.6310. Min Act: -0.1700
Data Index: 2948952 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.6310. Min Act: -0.1700
Data Index: 4398637 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5998. Min Act: -0.1700
Data Index: 8690166 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5685. Min Act: -0.1700
Data Index: 6853262 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5685. Min Act: -0.1700
Data Index: 1413301 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5685. Min Act: -0.1699
Data Index: 3938906 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5685. Min Act: -0.1700
Data Index: 719851 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5373. Min Act: -0.1700
Data Index: 2111692 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5060. Min Act: -0.1700
Data Index: 4046510 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5373. Min Act: -0.1700
Data Index: 522837 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5060. Min Act: -0.1700
Data Index: 2885062 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5060. Min Act: -0.1700
Data Index: 8493545 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.4748. Min Act: -0.1700
Data Index: 4826326 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.4748. Min Act: -0.1700
Data Index: 4037278 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19