Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 521 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2013. Min Range: -8.2013
Max Act: 8.2013. Min Act: -0.1700
Data Index: 6519006 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.8888. Min Act: -0.1700
Data Index: 8166942 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.7638. Min Act: -0.1700
Data Index: 7812963 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.7638. Min Act: -0.1700
Data Index: 1577710 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.6700. Min Act: -0.1700
Data Index: 8586549 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.6075. Min Act: -0.1700
Data Index: 6383722 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.5763. Min Act: -0.1700
Data Index: 4318314 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.5138. Min Act: -0.1700
Data Index: 8000621 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.4513. Min Act: -0.1700
Data Index: 2198012 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.4513. Min Act: -0.1700
Data Index: 5150724 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.4200. Min Act: -0.1700
Data Index: 862791 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.4200. Min Act: -0.1700
Data Index: 768462 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.3575. Min Act: -0.1700
Data Index: 5149007 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.3263. Min Act: -0.1700
Data Index: 1972885 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.3263. Min Act: -0.1700
Data Index: 1066466 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.3263. Min Act: -0.1700
Data Index: 1958060 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.2638. Min Act: -0.1700
Data Index: 4391871 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.2638. Min Act: -0.1700
Data Index: 3093049 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.2638. Min Act: -0.1700
Data Index: 2569962 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2013. Min Range: -8.2013
Max Act: 7.2325. Min Act: -0.1700
Data Index: 4862594 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19