Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5639 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.7440. Min Act: -0.1700
Data Index: 7438092 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.6815. Min Act: -0.1700
Data Index: 1836021 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.7127. Min Act: -0.1700
Data Index: 5422869 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.6190. Min Act: -0.1700
Data Index: 4674816 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.6190. Min Act: -0.1700
Data Index: 1494048 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.6502. Min Act: -0.1700
Data Index: 5803330 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.5877. Min Act: -0.1700
Data Index: 5451321 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.5877. Min Act: -0.1700
Data Index: 7983788 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.5877. Min Act: -0.1700
Data Index: 3583052 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.5877. Min Act: -0.1700
Data Index: 1072520 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.5565. Min Act: -0.1700
Data Index: 2567351 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.5565. Min Act: -0.1700
Data Index: 8129019 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.5565. Min Act: -0.1700
Data Index: 6684593 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.5565. Min Act: -0.1700
Data Index: 248663 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.4940. Min Act: -0.1700
Data Index: 6987828 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.4627. Min Act: -0.1700
Data Index: 2630283 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.4940. Min Act: -0.1700
Data Index: 6338043 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.4627. Min Act: -0.1700
Data Index: 5347811 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.4940. Min Act: -0.1700
Data Index: 925049 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7440. Min Range: -4.7440
Max Act: 4.4627. Min Act: -0.1700
Data Index: 3247656 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19