Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5899 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.7725. Min Act: -0.1700
Data Index: 7575809 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6788. Min Act: -0.1699
Data Index: 890924 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6163. Min Act: -0.1700
Data Index: 849578 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6163. Min Act: -0.1700
Data Index: 5649855 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6163. Min Act: -0.1700
Data Index: 4378277 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5850. Min Act: -0.1700
Data Index: 3267519 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5850. Min Act: -0.1700
Data Index: 3150104 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5538. Min Act: -0.1700
Data Index: 178970 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4600. Min Act: -0.1700
Data Index: 7832079 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4913. Min Act: -0.1700
Data Index: 1813041 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4600. Min Act: -0.1700
Data Index: 931654 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4600. Min Act: -0.1700
Data Index: 2797715 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4288. Min Act: -0.1700
Data Index: 890926 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.3975. Min Act: -0.1700
Data Index: 7068427 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4600. Min Act: -0.1700
Data Index: 8068324 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.3975. Min Act: -0.1700
Data Index: 7058827 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.3975. Min Act: -0.1700
Data Index: 1878184 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4288. Min Act: -0.1700
Data Index: 7012723 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.3975. Min Act: -0.1700
Data Index: 6271976 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.3975. Min Act: -0.1700
Data Index: 3728107 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19