Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5386 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.5517. Min Act: -0.1700
Data Index: 1405411 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.5204. Min Act: -0.1700
Data Index: 4958895 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.5204. Min Act: -0.1700
Data Index: 1335465 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4892. Min Act: -0.1700
Data Index: 8135502 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4892. Min Act: -0.1700
Data Index: 6651758 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4579. Min Act: -0.1700
Data Index: 5593152 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4579. Min Act: -0.1700
Data Index: 5014180 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4579. Min Act: -0.1700
Data Index: 5184006 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4579. Min Act: -0.1700
Data Index: 4130340 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3954. Min Act: -0.1700
Data Index: 7399089 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3954. Min Act: -0.1700
Data Index: 3296568 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3954. Min Act: -0.1700
Data Index: 3089278 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3329. Min Act: -0.1700
Data Index: 6216313 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3017. Min Act: -0.1700
Data Index: 8269472 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2392. Min Act: -0.1700
Data Index: 241303 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2079. Min Act: -0.1700
Data Index: 6930665 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2079. Min Act: -0.1700
Data Index: 3729793 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2079. Min Act: -0.1700
Data Index: 1449821 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.1767. Min Act: -0.1700
Data Index: 7763283 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.1767. Min Act: -0.1700
Data Index: 88302 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19