Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2810 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.6460. Min Act: -0.1700
Data Index: 6864894 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.6616. Min Act: -0.1700
Data Index: 4877713 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5677. Min Act: -0.1700
Data Index: 4749309 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5834. Min Act: -0.1700
Data Index: 4749310 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5677. Min Act: -0.1700
Data Index: 1598613 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5521. Min Act: -0.1700
Data Index: 4749308 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5364. Min Act: -0.1700
Data Index: 5259219 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5364. Min Act: -0.1700
Data Index: 89789 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5364. Min Act: -0.1700
Data Index: 2756298 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5208. Min Act: -0.1700
Data Index: 6768262 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 5119778 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 4241824 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 2825662 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 6693948 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 5620464 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 5351830 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 5225705 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 2707843 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 1998786 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 1126894 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19