Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1406 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.9111. Min Act: -0.1700
Data Index: 5489435 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.8486. Min Act: -0.1700
Data Index: 3027327 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.6611. Min Act: -0.1700
Data Index: 5905191 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.6298. Min Act: -0.1700
Data Index: 6238640 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.6298. Min Act: -0.1700
Data Index: 654787 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.5673. Min Act: -0.1700
Data Index: 3652486 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.5361. Min Act: -0.1699
Data Index: 2306832 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.5048. Min Act: -0.1700
Data Index: 7994733 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.5048. Min Act: -0.1700
Data Index: 7145180 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.4736. Min Act: -0.1700
Data Index: 6311462 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.4423. Min Act: -0.1700
Data Index: 3840351 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.4423. Min Act: -0.1700
Data Index: 2026611 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.4423. Min Act: -0.1700
Data Index: 442068 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.4111. Min Act: -0.1700
Data Index: 6816301 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.3798. Min Act: -0.1700
Data Index: 1741735 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.4111. Min Act: -0.1700
Data Index: 6633047 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.3798. Min Act: -0.1700
Data Index: 1638207 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.3798. Min Act: -0.1700
Data Index: 4591505 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.3798. Min Act: -0.1700
Data Index: 1633696 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9111. Min Range: -5.9111
Max Act: 5.3486. Min Act: -0.1700
Data Index: 7403032 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19