Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1747 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.9709. Min Act: -0.1700
Data Index: 4517433 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0021. Min Range: -4.0021
Max Act: 4.0021. Min Act: -0.1700
Data Index: 4681847 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.9396. Min Act: -0.1700
Data Index: 4746451 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.9083. Min Act: -0.1700
Data Index: 4595884 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8771. Min Act: -0.1700
Data Index: 7194647 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8458. Min Act: -0.1700
Data Index: 3268151 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8458. Min Act: -0.1700
Data Index: 1578602 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8771. Min Act: -0.1700
Data Index: 8733223 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8771. Min Act: -0.1700
Data Index: 3402313 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8458. Min Act: -0.1700
Data Index: 3096473 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8458. Min Act: -0.1700
Data Index: 8260910 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8145. Min Act: -0.1700
Data Index: 2007412 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8145. Min Act: -0.1700
Data Index: 5644097 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8145. Min Act: -0.1700
Data Index: 6536735 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8145. Min Act: -0.1700
Data Index: 747976 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.8145. Min Act: -0.1700
Data Index: 7700790 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.7833. Min Act: -0.1700
Data Index: 12602 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.7833. Min Act: -0.1700
Data Index: 7261522 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.7833. Min Act: -0.1700
Data Index: 3651246 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0021. Min Range: -4.0021
Max Act: 3.7833. Min Act: -0.1700
Data Index: 2065365 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19