Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3849 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.8019. Min Act: -0.1700
Data Index: 8377428 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.7394. Min Act: -0.1700
Data Index: 6904988 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.6768. Min Act: -0.1700
Data Index: 1674940 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.6455. Min Act: -0.1700
Data Index: 6607728 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.6455. Min Act: -0.1700
Data Index: 5601189 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.6612. Min Act: -0.1700
Data Index: 2965520 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5986. Min Act: -0.1700
Data Index: 1805621 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5829. Min Act: -0.1700
Data Index: 1273656 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5673. Min Act: -0.1700
Data Index: 1532765 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5516. Min Act: -0.1700
Data Index: 5971547 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5673. Min Act: -0.1700
Data Index: 740610 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5516. Min Act: -0.1700
Data Index: 6806906 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5203. Min Act: -0.1700
Data Index: 4356225 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5516. Min Act: -0.1700
Data Index: 3001872 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5360. Min Act: -0.1700
Data Index: 477641 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5516. Min Act: -0.1700
Data Index: 73828 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5673. Min Act: -0.1700
Data Index: 4821172 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5516. Min Act: -0.1700
Data Index: 4908882 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5360. Min Act: -0.1700
Data Index: 3121839 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8019. Min Range: -3.8019
Max Act: 3.5360. Min Act: -0.1700
Data Index: 7401709 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19