Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4833 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.4392. Min Act: -0.1700
Data Index: 3578815 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.2981. Min Act: -0.1700
Data Index: 3230951 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.2824. Min Act: -0.1700
Data Index: 838325 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.2195. Min Act: -0.1700
Data Index: 477666 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1881. Min Act: -0.1700
Data Index: 88065 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.2038. Min Act: -0.1700
Data Index: 4290931 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1881. Min Act: -0.1700
Data Index: 878414 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1566. Min Act: -0.1700
Data Index: 1495418 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1566. Min Act: -0.1700
Data Index: 934061 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1408. Min Act: -0.1700
Data Index: 7963261 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1566. Min Act: -0.1700
Data Index: 7077863 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1566. Min Act: -0.1700
Data Index: 694132 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1566. Min Act: -0.1700
Data Index: 314232 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1251. Min Act: -0.1700
Data Index: 7135542 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1251. Min Act: -0.1700
Data Index: 8069888 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1408. Min Act: -0.1700
Data Index: 7907149 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1251. Min Act: -0.1700
Data Index: 4589901 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1408. Min Act: -0.1700
Data Index: 8566692 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1251. Min Act: -0.1700
Data Index: 4844132 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4392. Min Range: -3.4392
Max Act: 3.1251. Min Act: -0.1700
Data Index: 6208031 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19