Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8427. Min Range: -12.8427
Max Act: 12.8427. Min Act: -0.1700
Data Index: 7418686 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8427. Min Range: -12.8427
Max Act: 12.0927. Min Act: -0.1700
Data Index: 7333992 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8427. Min Range: -12.8427
Max Act: 12.0302. Min Act: -0.1700
Data Index: 955296 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.8427. Min Act: -0.1700
Data Index: 4329765 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.8427. Min Act: -0.1700
Data Index: 6383172 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.5927. Min Act: -0.1700
Data Index: 588119 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.4677. Min Act: -0.1700
Data Index: 5810797 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.4052. Min Act: -0.1700
Data Index: 1393684 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.4677. Min Act: -0.1700
Data Index: 1546200 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.3427. Min Act: -0.1695
Data Index: 3448806 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.3427. Min Act: -0.1700
Data Index: 5985785 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.3427. Min Act: -0.1699
Data Index: 5102599 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.2802. Min Act: -0.1700
Data Index: 586874 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.2802. Min Act: -0.1696
Data Index: 7543355 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.2802. Min Act: -0.1700
Data Index: 3154875 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.2177. Min Act: -0.1700
Data Index: 7819095 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.2177. Min Act: -0.1700
Data Index: 7361667 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.2177. Min Act: -0.1700
Data Index: 1788845 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.1552. Min Act: -0.1700
Data Index: 7202722 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8427. Min Range: -12.8427
Max Act: 11.1552. Min Act: -0.1700
Data Index: 1111608 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19