Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2938 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.5308. Min Act: -0.1700
Data Index: 6185970 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.4370. Min Act: -0.1700
Data Index: 1316467 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.3433. Min Act: -0.1700
Data Index: 8334852 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.3120. Min Act: -0.1700
Data Index: 3908045 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.2808. Min Act: -0.1700
Data Index: 7179820 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.2495. Min Act: -0.1700
Data Index: 3342471 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.2495. Min Act: -0.1700
Data Index: 473021 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.2495. Min Act: -0.1700
Data Index: 4065521 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.2183. Min Act: -0.1700
Data Index: 5383286 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1870. Min Act: -0.1700
Data Index: 1224760 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1870. Min Act: -0.1700
Data Index: 4472199 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1558. Min Act: -0.1700
Data Index: 1858999 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1558. Min Act: -0.1700
Data Index: 876594 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1558. Min Act: -0.1700
Data Index: 863817 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1245. Min Act: -0.1700
Data Index: 376163 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1245. Min Act: -0.1700
Data Index: 1648197 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1245. Min Act: -0.1700
Data Index: 6640462 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1245. Min Act: -0.1700
Data Index: 3093441 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1245. Min Act: -0.1700
Data Index: 6128570 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5308. Min Range: -4.5308
Max Act: 4.1245. Min Act: -0.1700
Data Index: 930388 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19