Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.3665. Min Act: -0.1700
Data Index: 558857 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.3352. Min Act: -0.1700
Data Index: 6613853 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.3040. Min Act: -0.1700
Data Index: 7987243 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.2415. Min Act: -0.1700
Data Index: 1286669 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.2415. Min Act: -0.1700
Data Index: 4948036 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1790. Min Act: -0.1700
Data Index: 5256158 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.2102. Min Act: -0.1699
Data Index: 1806277 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.2415. Min Act: -0.1700
Data Index: 5538856 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1790. Min Act: -0.1700
Data Index: 6694628 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1790. Min Act: -0.1700
Data Index: 362748 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1790. Min Act: -0.1700
Data Index: 7015033 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1790. Min Act: -0.1700
Data Index: 2688346 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1477. Min Act: -0.1700
Data Index: 6475062 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1477. Min Act: -0.1700
Data Index: 3546385 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1477. Min Act: -0.1700
Data Index: 8635771 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1477. Min Act: -0.1700
Data Index: 7681862 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1477. Min Act: -0.1700
Data Index: 6410197 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1790. Min Act: -0.1700
Data Index: 7160009 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1477. Min Act: -0.1700
Data Index: 6365547 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3665. Min Range: -6.3665
Max Act: 6.1477. Min Act: -0.1700
Data Index: 2950245 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19