Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1553 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4517. Min Range: -7.4517
Max Act: 7.4517. Min Act: -0.1700
Data Index: 7620829 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4517. Min Range: -7.4517
Max Act: 7.3892. Min Act: -0.1700
Data Index: 8141382 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4517. Min Range: -7.4517
Max Act: 7.2642. Min Act: -0.1700
Data Index: 3205017 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4517. Min Range: -7.4517
Max Act: 7.2329. Min Act: -0.1700
Data Index: 2630694 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4517. Min Range: -7.4517
Max Act: 7.0767. Min Act: -0.1700
Data Index: 2986777 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4517. Min Range: -7.4517
Max Act: 7.0454. Min Act: -0.1700
Data Index: 5348500 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4517. Min Range: -7.4517
Max Act: 7.0454. Min Act: -0.1700
Data Index: 1556847 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4517. Min Range: -7.4517
Max Act: 7.0767. Min Act: -0.1700
Data Index: 3277356 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4517. Min Range: -7.4517
Max Act: 7.0142. Min Act: -0.1700
Data Index: 3839873 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.9829. Min Act: -0.1700
Data Index: 3888328 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.9829. Min Act: -0.1700
Data Index: 6662389 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.9517. Min Act: -0.1700
Data Index: 6707216 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.9204. Min Act: -0.1700
Data Index: 7496080 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.9204. Min Act: -0.1700
Data Index: 3549300 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.8579. Min Act: -0.1700
Data Index: 244168 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.8892. Min Act: -0.1700
Data Index: 4116793 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.8892. Min Act: -0.1700
Data Index: 4095155 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.8579. Min Act: -0.1700
Data Index: 3239185 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.8579. Min Act: -0.1700
Data Index: 5962622 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4517. Min Range: -7.4517
Max Act: 6.8579. Min Act: -0.1700
Data Index: 2409418 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19