Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3866 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.8051. Min Act: -0.1700
Data Index: 8304532 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.8137. Min Act: -0.1696
Data Index: 1262177 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.8223. Min Act: -0.1700
Data Index: 7719142 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7965. Min Act: -0.1700
Data Index: 4638778 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7793. Min Act: -0.1700
Data Index: 6274074 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7620. Min Act: -0.1700
Data Index: 1000841 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7706. Min Act: -0.1658
Data Index: 7068467 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7706. Min Act: -0.1700
Data Index: 828110 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7620. Min Act: -0.1700
Data Index: 6273984 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7534. Min Act: -0.1700
Data Index: 1851807 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7447. Min Act: -0.1700
Data Index: 601942 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7534. Min Act: -0.1700
Data Index: 634453 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7447. Min Act: -0.1700
Data Index: 6808992 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7447. Min Act: -0.1700
Data Index: 3612496 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7275. Min Act: -0.1663
Data Index: 6015523 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7361. Min Act: -0.1696
Data Index: 7607893 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7361. Min Act: -0.1700
Data Index: 1876634 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7361. Min Act: -0.1700
Data Index: 540296 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7275. Min Act: -0.1700
Data Index: 1000842 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8223. Min Range: -1.8223
Max Act: 1.7361. Min Act: -0.1700
Data Index: 6569399 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19