Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0939. Min Range: -6.0939
Max Act: 6.0939. Min Act: -0.1700
Data Index: 1598421 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0939. Min Range: -6.0939
Max Act: 6.0001. Min Act: -0.1700
Data Index: 2409261 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.9376. Min Act: -0.1700
Data Index: 1971224 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.8751. Min Act: -0.1700
Data Index: 601671 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.8751. Min Act: -0.1700
Data Index: 6523971 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.8751. Min Act: -0.1700
Data Index: 5014699 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.8751. Min Act: -0.1700
Data Index: 528106 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.7814. Min Act: -0.1700
Data Index: 5525735 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.7501. Min Act: -0.1700
Data Index: 4217164 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.7189. Min Act: -0.1700
Data Index: 3232720 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.7189. Min Act: -0.1700
Data Index: 1709659 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.7189. Min Act: -0.1700
Data Index: 4300337 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.6876. Min Act: -0.1700
Data Index: 2617124 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.6876. Min Act: -0.1700
Data Index: 6433566 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.6251. Min Act: -0.1700
Data Index: 6817732 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.6564. Min Act: -0.1700
Data Index: 3464621 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.6564. Min Act: -0.1700
Data Index: 114303 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.6564. Min Act: -0.1700
Data Index: 3464625 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.6564. Min Act: -0.1700
Data Index: 5836989 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0939. Min Range: -6.0939
Max Act: 5.6251. Min Act: -0.1700
Data Index: 2346166 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19