Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2764 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2684. Min Range: -4.2684
Max Act: 4.2684. Min Act: -0.1700
Data Index: 467397 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2684. Min Range: -4.2684
Max Act: 4.1121. Min Act: -0.1700
Data Index: 3357031 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.9871. Min Act: -0.1700
Data Index: 5340107 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.9246. Min Act: -0.1700
Data Index: 3482937 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.8621. Min Act: -0.1700
Data Index: 5548977 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.8621. Min Act: -0.1700
Data Index: 1353996 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.8308. Min Act: -0.1700
Data Index: 8727650 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.8308. Min Act: -0.1700
Data Index: 723196 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.8308. Min Act: -0.1700
Data Index: 370149 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.8621. Min Act: -0.1700
Data Index: 6211938 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.8308. Min Act: -0.1700
Data Index: 5725962 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.7995. Min Act: -0.1700
Data Index: 3886350 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.7839. Min Act: -0.1700
Data Index: 6164856 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.7995. Min Act: -0.1700
Data Index: 2080565 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.7995. Min Act: -0.1700
Data Index: 7910777 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.7839. Min Act: -0.1700
Data Index: 8060009 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.7839. Min Act: -0.1700
Data Index: 7013391 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.7682. Min Act: -0.1700
Data Index: 3863056 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.7839. Min Act: -0.1700
Data Index: 3709595 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2684. Min Range: -4.2684
Max Act: 3.7995. Min Act: -0.1700
Data Index: 1793729 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19