Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2111. Min Range: -7.2111
Max Act: 7.2111. Min Act: -0.1700
Data Index: 8559893 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2111. Min Range: -7.2111
Max Act: 7.1486. Min Act: -0.1700
Data Index: 5264527 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2111. Min Range: -7.2111
Max Act: 7.0236. Min Act: -0.1700
Data Index: 8762100 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.9611. Min Act: -0.1700
Data Index: 1842599 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.8986. Min Act: -0.1700
Data Index: 645881 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.8361. Min Act: -0.1700
Data Index: 3343012 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.8361. Min Act: -0.1700
Data Index: 5570333 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.8361. Min Act: -0.1700
Data Index: 724972 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.8361. Min Act: -0.1700
Data Index: 3590775 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.8048. Min Act: -0.1700
Data Index: 6298925 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.7423. Min Act: -0.1700
Data Index: 2000470 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.6798. Min Act: -0.1700
Data Index: 4583901 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.7111. Min Act: -0.1700
Data Index: 6391906 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.6798. Min Act: -0.1700
Data Index: 4030030 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.6798. Min Act: -0.1700
Data Index: 7838866 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.6486. Min Act: -0.1700
Data Index: 593151 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.6173. Min Act: -0.1700
Data Index: 2712258 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.6173. Min Act: -0.1700
Data Index: 224121 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.6173. Min Act: -0.1700
Data Index: 2659506 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2111. Min Range: -7.2111
Max Act: 6.5861. Min Act: -0.1700
Data Index: 4959559 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19