Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5800 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2392. Min Range: -12.2392
Max Act: 12.2392. Min Act: -0.1700
Data Index: 4504136 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2392. Min Range: -12.2392
Max Act: 12.0517. Min Act: -0.1700
Data Index: 6712172 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.9892. Min Act: -0.1700
Data Index: 6712168 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2392. Min Range: -12.2392
Max Act: 12.0517. Min Act: -0.1700
Data Index: 3897013 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.9267. Min Act: -0.1700
Data Index: 2021943 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.9267. Min Act: -0.1700
Data Index: 2403848 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.9892. Min Act: -0.1700
Data Index: 5686682 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.8642. Min Act: -0.1700
Data Index: 2266835 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.8642. Min Act: -0.1700
Data Index: 162301 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.8642. Min Act: -0.1700
Data Index: 8522368 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.8017. Min Act: -0.1700
Data Index: 5830167 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.7392. Min Act: -0.1700
Data Index: 7327689 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.7392. Min Act: -0.1700
Data Index: 7857679 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.7392. Min Act: -0.1700
Data Index: 3867032 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.8017. Min Act: -0.1700
Data Index: 4421661 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.6142. Min Act: -0.1700
Data Index: 4504137 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.7392. Min Act: -0.1700
Data Index: 6424544 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.6767. Min Act: -0.1700
Data Index: 2681414 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.6767. Min Act: -0.1700
Data Index: 3649793 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2392. Min Range: -12.2392
Max Act: 11.6767. Min Act: -0.1700
Data Index: 2046851 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19