Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5465 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.2173. Min Act: -0.1700
Data Index: 5919594 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.2173. Min Act: -0.1700
Data Index: 7252504 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.1861. Min Act: -0.1700
Data Index: 5360803 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.1861. Min Act: -0.1700
Data Index: 115165 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.1548. Min Act: -0.1700
Data Index: 5192447 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.1548. Min Act: -0.1700
Data Index: 2482539 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.1548. Min Act: -0.1700
Data Index: 4259521 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.1236. Min Act: -0.1700
Data Index: 6268305 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.0611. Min Act: -0.1700
Data Index: 6208330 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.0923. Min Act: -0.1700
Data Index: 8638081 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.0923. Min Act: -0.1700
Data Index: 6435454 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.0611. Min Act: -0.1700
Data Index: 6435459 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.0611. Min Act: -0.1700
Data Index: 4061918 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2173. Min Range: -5.2173
Max Act: 4.9986. Min Act: -0.1700
Data Index: 6477707 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.0298. Min Act: -0.1700
Data Index: 5192454 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2173. Min Range: -5.2173
Max Act: 4.9986. Min Act: -0.1700
Data Index: 4416248 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2173. Min Range: -5.2173
Max Act: 5.0298. Min Act: -0.1700
Data Index: 115170 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2173. Min Range: -5.2173
Max Act: 4.9986. Min Act: -0.1700
Data Index: 7101946 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2173. Min Range: -5.2173
Max Act: 4.9986. Min Act: -0.1700
Data Index: 5540767 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2173. Min Range: -5.2173
Max Act: 4.9986. Min Act: -0.1700
Data Index: 8610020 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19