Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 721 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.9055. Min Act: -0.1700
Data Index: 838323 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.7805. Min Act: -0.1700
Data Index: 4249786 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.7805. Min Act: -0.1700
Data Index: 1739514 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.7805. Min Act: -0.1700
Data Index: 1135590 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.7492. Min Act: -0.1700
Data Index: 7012146 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.6867. Min Act: -0.1700
Data Index: 8202742 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.6555. Min Act: -0.1700
Data Index: 5736360 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.6555. Min Act: -0.1700
Data Index: 1327260 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.6555. Min Act: -0.1700
Data Index: 7841027 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.6555. Min Act: -0.1700
Data Index: 7047147 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.6242. Min Act: -0.1700
Data Index: 356025 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.5930. Min Act: -0.1700
Data Index: 4524699 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.5305. Min Act: -0.1700
Data Index: 8352812 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.5617. Min Act: -0.1700
Data Index: 3551015 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.5305. Min Act: -0.1700
Data Index: 1385499 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.5305. Min Act: -0.1700
Data Index: 6474032 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.5305. Min Act: -0.1700
Data Index: 1666942 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.5305. Min Act: -0.1700
Data Index: 2256668 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.5617. Min Act: -0.1700
Data Index: 5215414 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9055. Min Range: -4.9055
Max Act: 4.4992. Min Act: -0.1700
Data Index: 6774910 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19