Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0434. Min Range: -7.0434
Max Act: 7.0434. Min Act: -0.1700
Data Index: 7488986 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.6996. Min Act: -0.1700
Data Index: 5636052 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.6684. Min Act: -0.1700
Data Index: 4246276 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.6059. Min Act: -0.1700
Data Index: 8070561 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.5746. Min Act: -0.1700
Data Index: 1831809 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.5121. Min Act: -0.1700
Data Index: 2052020 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.5434. Min Act: -0.1700
Data Index: 1864510 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.5121. Min Act: -0.1700
Data Index: 4329578 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.5434. Min Act: -0.1700
Data Index: 3611122 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.4809. Min Act: -0.1700
Data Index: 5316614 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.4496. Min Act: -0.1700
Data Index: 4496734 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.4496. Min Act: -0.1700
Data Index: 4496740 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.4496. Min Act: -0.1700
Data Index: 5704696 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.4184. Min Act: -0.1700
Data Index: 2400458 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.3871. Min Act: -0.1700
Data Index: 5289766 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.3559. Min Act: -0.1700
Data Index: 5785568 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.4184. Min Act: -0.1700
Data Index: 6537606 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.3871. Min Act: -0.1700
Data Index: 2400449 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.3871. Min Act: -0.1700
Data Index: 5137131 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0434. Min Range: -7.0434
Max Act: 6.4184. Min Act: -0.1700
Data Index: 2586942 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19