Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.9613. Min Act: -0.1700
Data Index: 8827463 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.9440. Min Act: -0.1690
Data Index: 1440393 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8755. Min Act: -0.1700
Data Index: 1213661 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8755. Min Act: -0.1638
Data Index: 378139 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8755. Min Act: -0.1700
Data Index: 5708477 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8755. Min Act: -0.1700
Data Index: 5846594 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8585. Min Act: -0.1700
Data Index: 6369802 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8585. Min Act: -0.1700
Data Index: 8235068 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8585. Min Act: -0.1685
Data Index: 786714 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8585. Min Act: -0.1697
Data Index: 5635756 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8585. Min Act: -0.1690
Data Index: 3135430 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8415. Min Act: -0.1699
Data Index: 6404866 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8415. Min Act: -0.1694
Data Index: 1873869 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8246. Min Act: -0.1700
Data Index: 3427072 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8246. Min Act: -0.1698
Data Index: 1081143 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8246. Min Act: -0.1697
Data Index: 8135323 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8246. Min Act: -0.1602
Data Index: 7555435 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8246. Min Act: -0.1697
Data Index: 5155871 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8246. Min Act: -0.1665
Data Index: 4392134 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9613. Min Range: -0.9613
Max Act: 0.8246. Min Act: -0.1700
Data Index: 1693784 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19