Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 869 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.4722. Min Act: -0.1700
Data Index: 5842564 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.3160. Min Act: -0.1700
Data Index: 481683 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.2222. Min Act: -0.1700
Data Index: 1868659 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.1910. Min Act: -0.1700
Data Index: 6894533 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.1910. Min Act: -0.1700
Data Index: 4634549 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.1597. Min Act: -0.1700
Data Index: 6834348 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.1285. Min Act: -0.1700
Data Index: 3070472 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.1285. Min Act: -0.1700
Data Index: 7855989 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.1597. Min Act: -0.1700
Data Index: 4807394 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.0972. Min Act: -0.1700
Data Index: 1172890 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.0972. Min Act: -0.1700
Data Index: 2593329 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.0347. Min Act: -0.1700
Data Index: 1754688 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.0347. Min Act: -0.1700
Data Index: 5214223 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.0347. Min Act: -0.1700
Data Index: 155575 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.0347. Min Act: -0.1700
Data Index: 5971355 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4722. Min Range: -6.4722
Max Act: 6.0347. Min Act: -0.1700
Data Index: 2637478 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4722. Min Range: -6.4722
Max Act: 5.9410. Min Act: -0.1700
Data Index: 2835670 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4722. Min Range: -6.4722
Max Act: 5.9097. Min Act: -0.1700
Data Index: 3024400 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4722. Min Range: -6.4722
Max Act: 5.9410. Min Act: -0.1700
Data Index: 1819860 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4722. Min Range: -6.4722
Max Act: 5.9097. Min Act: -0.1700
Data Index: 3600598 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19