Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2871. Min Range: -3.2871
Max Act: 3.2871. Min Act: -0.1700
Data Index: 1988388 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2871. Min Range: -3.2871
Max Act: 3.1928. Min Act: -0.1700
Data Index: 7244478 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2871. Min Range: -3.2871
Max Act: 3.1298. Min Act: -0.1700
Data Index: 6979925 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2871. Min Range: -3.2871
Max Act: 3.1298. Min Act: -0.1700
Data Index: 483309 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2871. Min Range: -3.2871
Max Act: 3.0510. Min Act: -0.1700
Data Index: 1046801 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2871. Min Range: -3.2871
Max Act: 3.0668. Min Act: -0.1700
Data Index: 3352308 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9720. Min Act: -0.1700
Data Index: 7813864 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9878. Min Act: -0.1700
Data Index: 4297360 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2871. Min Range: -3.2871
Max Act: 3.0352. Min Act: -0.1700
Data Index: 7923143 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9878. Min Act: -0.1700
Data Index: 4064423 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9562. Min Act: -0.1700
Data Index: 5453818 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9878. Min Act: -0.1700
Data Index: 5977583 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9720. Min Act: -0.1700
Data Index: 1608462 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9562. Min Act: -0.1700
Data Index: 7835491 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9562. Min Act: -0.1700
Data Index: 1717018 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9720. Min Act: -0.1700
Data Index: 4481517 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9562. Min Act: -0.1700
Data Index: 4711739 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9404. Min Act: -0.1700
Data Index: 7645525 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9562. Min Act: -0.1700
Data Index: 6396594 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2871. Min Range: -3.2871
Max Act: 2.9404. Min Act: -0.1700
Data Index: 1918937 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19