Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1785. Min Range: -5.1785
Max Act: 5.1785. Min Act: -0.1700
Data Index: 7522196 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1785. Min Range: -5.1785
Max Act: 5.1473. Min Act: -0.1700
Data Index: 8346577 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1785. Min Range: -5.1785
Max Act: 5.0535. Min Act: -0.1700
Data Index: 6397241 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1785. Min Range: -5.1785
Max Act: 5.0848. Min Act: -0.1700
Data Index: 8430820 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1785. Min Range: -5.1785
Max Act: 5.0535. Min Act: -0.1700
Data Index: 5183351 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1785. Min Range: -5.1785
Max Act: 5.0535. Min Act: -0.1700
Data Index: 376410 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.9910. Min Act: -0.1700
Data Index: 5748604 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.9598. Min Act: -0.1700
Data Index: 7986905 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.9598. Min Act: -0.1700
Data Index: 3798893 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.9598. Min Act: -0.1700
Data Index: 6181947 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.9598. Min Act: -0.1700
Data Index: 8575948 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.9285. Min Act: -0.1700
Data Index: 5325923 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.9598. Min Act: -0.1700
Data Index: 421696 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2139491 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.8973. Min Act: -0.1700
Data Index: 7123139 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.8973. Min Act: -0.1700
Data Index: 8687433 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.8660. Min Act: -0.1700
Data Index: 2133944 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.8973. Min Act: -0.1700
Data Index: 5768884 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.8973. Min Act: -0.1700
Data Index: 6322188 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1785. Min Range: -5.1785
Max Act: 4.8348. Min Act: -0.1700
Data Index: 344291 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19