Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1945 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6548. Min Range: -6.6548
Max Act: 6.6548. Min Act: -0.1700
Data Index: 7833129 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6548. Min Range: -6.6548
Max Act: 6.3735. Min Act: -0.1700
Data Index: 4526813 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6548. Min Range: -6.6548
Max Act: 6.2485. Min Act: -0.1700
Data Index: 798215 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6548. Min Range: -6.6548
Max Act: 6.0923. Min Act: -0.1700
Data Index: 8307637 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.9985. Min Act: -0.1700
Data Index: 90143 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6548. Min Range: -6.6548
Max Act: 6.0298. Min Act: -0.1700
Data Index: 1360329 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6548. Min Range: -6.6548
Max Act: 6.0298. Min Act: -0.1700
Data Index: 2877125 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.9360. Min Act: -0.1700
Data Index: 4699821 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.9360. Min Act: -0.1700
Data Index: 2040658 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.9360. Min Act: -0.1700
Data Index: 8640858 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.9048. Min Act: -0.1700
Data Index: 6516371 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.8423. Min Act: -0.1700
Data Index: 4640105 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.8735. Min Act: -0.1700
Data Index: 3077923 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.8423. Min Act: -0.1700
Data Index: 7310000 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.8423. Min Act: -0.1700
Data Index: 2555861 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.7798. Min Act: -0.1700
Data Index: 7986949 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.7485. Min Act: -0.1700
Data Index: 3085351 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.7485. Min Act: -0.1700
Data Index: 4526814 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.8110. Min Act: -0.1700
Data Index: 2477391 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6548. Min Range: -6.6548
Max Act: 5.7485. Min Act: -0.1700
Data Index: 4715050 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19