Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6005 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8784. Min Range: -8.8784
Max Act: 8.8784. Min Act: -0.1700
Data Index: 1570572 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8784. Min Range: -8.8784
Max Act: 8.3784. Min Act: -0.1700
Data Index: 647248 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8784. Min Range: -8.8784
Max Act: 8.0346. Min Act: -0.1700
Data Index: 8782535 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.9409. Min Act: -0.1700
Data Index: 5349523 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.9409. Min Act: -0.1700
Data Index: 8221806 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.8784. Min Act: -0.1700
Data Index: 8363337 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.8159. Min Act: -0.1700
Data Index: 1914218 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.7846. Min Act: -0.1700
Data Index: 7843159 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.7846. Min Act: -0.1700
Data Index: 1001357 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.7221. Min Act: -0.1700
Data Index: 673431 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.7221. Min Act: -0.1700
Data Index: 5325213 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.6909. Min Act: -0.1700
Data Index: 8088752 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.6596. Min Act: -0.1700
Data Index: 7575958 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.6596. Min Act: -0.1700
Data Index: 1877746 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.6284. Min Act: -0.1700
Data Index: 8079454 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.5971. Min Act: -0.1700
Data Index: 4824186 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.5971. Min Act: -0.1700
Data Index: 8707869 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.5971. Min Act: -0.1700
Data Index: 5219689 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.5659. Min Act: -0.1700
Data Index: 3518941 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8784. Min Range: -8.8784
Max Act: 7.5659. Min Act: -0.1700
Data Index: 58880 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19