Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 585 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.5142. Min Act: -0.1700
Data Index: 2178744 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.4517. Min Act: -0.1700
Data Index: 3929439 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.3267. Min Act: -0.1700
Data Index: 4541566 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.2954. Min Act: -0.1700
Data Index: 7756921 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.2954. Min Act: -0.1700
Data Index: 500551 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.2642. Min Act: -0.1700
Data Index: 1001583 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.2642. Min Act: -0.1700
Data Index: 204162 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.2642. Min Act: -0.1700
Data Index: 1573592 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.1392. Min Act: -0.1700
Data Index: 1834991 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.1392. Min Act: -0.1700
Data Index: 3055733 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.1704. Min Act: -0.1700
Data Index: 5059817 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.1079. Min Act: -0.1700
Data Index: 5080366 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.0767. Min Act: -0.1700
Data Index: 3196630 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.1079. Min Act: -0.1700
Data Index: 7191886 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.1079. Min Act: -0.1700
Data Index: 7301520 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.1079. Min Act: -0.1700
Data Index: 3793986 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.1079. Min Act: -0.1700
Data Index: 2564406 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.1079. Min Act: -0.1700
Data Index: 6533442 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.0767. Min Act: -0.1700
Data Index: 1495878 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5142. Min Range: -6.5142
Max Act: 6.0454. Min Act: -0.1700
Data Index: 1401053 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19