Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 346 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.8579. Min Range: -16.8579
Max Act: 16.8579. Min Act: -0.1700
Data Index: 8361257 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.8579. Min Range: -16.8579
Max Act: 16.4829. Min Act: -0.1700
Data Index: 6130823 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.8579. Min Range: -16.8579
Max Act: 16.2329. Min Act: -0.1700
Data Index: 3671815 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.9829. Min Act: -0.1699
Data Index: 3300305 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.9829. Min Act: -0.1700
Data Index: 8361259 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.8579. Min Act: -0.1700
Data Index: 2983979 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.6079. Min Act: -0.1700
Data Index: 6092087 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.3579. Min Act: -0.1688
Data Index: 1854883 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.3579. Min Act: -0.1687
Data Index: 4042857 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.2954. Min Act: -0.1700
Data Index: 754516 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.1704. Min Act: -0.1700
Data Index: 1781856 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.1079. Min Act: -0.1698
Data Index: 468411 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.8579. Min Range: -16.8579
Max Act: 15.1079. Min Act: -0.1700
Data Index: 1255567 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.8579. Min Range: -16.8579
Max Act: 14.9829. Min Act: -0.1698
Data Index: 7497220 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.8579. Min Range: -16.8579
Max Act: 14.8579. Min Act: -0.1700
Data Index: 7960549 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.8579. Min Range: -16.8579
Max Act: 14.8579. Min Act: -0.1700
Data Index: 6136847 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.8579. Min Range: -16.8579
Max Act: 14.7954. Min Act: -0.1700
Data Index: 4717167 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.8579. Min Range: -16.8579
Max Act: 14.8579. Min Act: -0.1700
Data Index: 1592967 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.8579. Min Range: -16.8579
Max Act: 14.7954. Min Act: -0.1700
Data Index: 7515373 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.8579. Min Range: -16.8579
Max Act: 14.7954. Min Act: -0.1693
Data Index: 5474820 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19