Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5153 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 2475612 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 5975375 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 495402 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 2840626 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 3654161 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0284. Min Act: -0.1700
Data Index: 785339 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 2600429 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 1782666 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0284. Min Act: -0.1700
Data Index: 123721 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 1686080 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 3528544 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0284. Min Act: -0.1700
Data Index: 3412838 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 2455641 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 2314072 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 32669 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 3324431 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0284. Min Act: -0.1700
Data Index: 2067232 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 618203 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0909. Min Act: -0.1700
Data Index: 1446200 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0909. Min Range: -10.0909
Max Act: 10.0284. Min Act: -0.1700
Data Index: 3248305 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19