Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2817 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1990. Min Range: -9.1990
Max Act: 9.1990. Min Act: -0.1700
Data Index: 2144363 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1990. Min Range: -9.1990
Max Act: 9.0115. Min Act: -0.1700
Data Index: 5052916 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1990. Min Range: -9.1990
Max Act: 9.0115. Min Act: -0.1700
Data Index: 7743588 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1990. Min Range: -9.1990
Max Act: 9.0740. Min Act: -0.1700
Data Index: 7519511 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.9490. Min Act: -0.1700
Data Index: 2088190 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.8240. Min Act: -0.1700
Data Index: 5766825 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.7615. Min Act: -0.1700
Data Index: 1824291 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.8240. Min Act: -0.1700
Data Index: 7710656 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.6990. Min Act: -0.1700
Data Index: 6696921 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.6990. Min Act: -0.1700
Data Index: 2996683 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.6990. Min Act: -0.1700
Data Index: 555803 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.6990. Min Act: -0.1700
Data Index: 6942885 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.6990. Min Act: -0.1700
Data Index: 7109793 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.6990. Min Act: -0.1700
Data Index: 8203003 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.6365. Min Act: -0.1700
Data Index: 1357085 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.6365. Min Act: -0.1700
Data Index: 3816692 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.6365. Min Act: -0.1700
Data Index: 5863270 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.5740. Min Act: -0.1700
Data Index: 4610904 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.5740. Min Act: -0.1700
Data Index: 4066009 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1990. Min Range: -9.1990
Max Act: 8.5740. Min Act: -0.1700
Data Index: 564129 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19