Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5810 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.5100. Min Act: -0.1700
Data Index: 3896105 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.4475. Min Act: -0.1700
Data Index: 6243815 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.4475. Min Act: -0.1700
Data Index: 2814394 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.4162. Min Act: -0.1700
Data Index: 4665631 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.3850. Min Act: -0.1700
Data Index: 5367540 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.3850. Min Act: -0.1700
Data Index: 1022458 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.3537. Min Act: -0.1700
Data Index: 5402962 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.3537. Min Act: -0.1700
Data Index: 1097317 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.3537. Min Act: -0.1700
Data Index: 285070 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.3537. Min Act: -0.1700
Data Index: 5660206 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.3850. Min Act: -0.1700
Data Index: 1413081 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.3537. Min Act: -0.1700
Data Index: 2249091 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.3225. Min Act: -0.1700
Data Index: 5489814 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.2912. Min Act: -0.1700
Data Index: 7932556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.2600. Min Act: -0.1700
Data Index: 8588872 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.2600. Min Act: -0.1700
Data Index: 3182533 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.2600. Min Act: -0.1700
Data Index: 2320745 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.2600. Min Act: -0.1700
Data Index: 6793675 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.2287. Min Act: -0.1700
Data Index: 5931558 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5100. Min Range: -4.5100
Max Act: 4.1975. Min Act: -0.1700
Data Index: 4717454 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19