Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1517. Min Range: -6.1517
Max Act: 6.1517. Min Act: -0.1700
Data Index: 7553063 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1517. Min Range: -6.1517
Max Act: 6.0892. Min Act: -0.1700
Data Index: 5107441 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1517. Min Range: -6.1517
Max Act: 6.0579. Min Act: -0.1700
Data Index: 4298118 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1517. Min Range: -6.1517
Max Act: 6.0267. Min Act: -0.1700
Data Index: 607900 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1517. Min Range: -6.1517
Max Act: 6.0267. Min Act: -0.1700
Data Index: 6472312 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.9954. Min Act: -0.1700
Data Index: 6839317 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1517. Min Range: -6.1517
Max Act: 6.0267. Min Act: -0.1700
Data Index: 2840453 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.9642. Min Act: -0.1700
Data Index: 5704244 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.9329. Min Act: -0.1700
Data Index: 73024 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.9329. Min Act: -0.1700
Data Index: 4322796 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.9017. Min Act: -0.1700
Data Index: 1496218 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.8704. Min Act: -0.1700
Data Index: 8655367 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.9017. Min Act: -0.1700
Data Index: 8431724 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.9017. Min Act: -0.1700
Data Index: 7052333 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.8392. Min Act: -0.1700
Data Index: 5712626 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.8704. Min Act: -0.1700
Data Index: 7154996 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.8704. Min Act: -0.1700
Data Index: 6472313 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.8079. Min Act: -0.1700
Data Index: 531468 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.8392. Min Act: -0.1700
Data Index: 4409038 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1517. Min Range: -6.1517
Max Act: 5.8392. Min Act: -0.1700
Data Index: 3745146 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19