Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1668. Min Range: -8.1668
Max Act: 8.1668. Min Act: -0.1700
Data Index: 3307208 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1668. Min Range: -8.1668
Max Act: 8.0418. Min Act: -0.1700
Data Index: 6532445 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.9481. Min Act: -0.1700
Data Index: 5926314 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.8543. Min Act: -0.1700
Data Index: 2180651 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.7606. Min Act: -0.1700
Data Index: 4867014 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.8543. Min Act: -0.1700
Data Index: 6442218 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.7918. Min Act: -0.1700
Data Index: 3308165 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.7918. Min Act: -0.1700
Data Index: 7941408 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.7293. Min Act: -0.1700
Data Index: 4737147 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.6668. Min Act: -0.1700
Data Index: 573399 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.6668. Min Act: -0.1700
Data Index: 835814 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.6981. Min Act: -0.1700
Data Index: 726639 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.7293. Min Act: -0.1700
Data Index: 5965506 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.6981. Min Act: -0.1700
Data Index: 8086263 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.6356. Min Act: -0.1700
Data Index: 518005 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.5731. Min Act: -0.1700
Data Index: 1151415 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.6043. Min Act: -0.1700
Data Index: 6183869 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.6356. Min Act: -0.1700
Data Index: 4425426 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.5731. Min Act: -0.1700
Data Index: 5059103 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1668. Min Range: -8.1668
Max Act: 7.6043. Min Act: -0.1700
Data Index: 6381456 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19