Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1219 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1336. Min Act: -0.0001
Data Index: 1588752 (Python Code)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1268. Min Act: -0.0001
Data Index: 832182 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1266. Min Act: -0.0001
Data Index: 85090 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1222. Min Act: -0.0001
Data Index: 2438 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1247. Min Act: -0.0001
Data Index: 700857 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1189. Min Act: -0.0001
Data Index: 1458690 (Python Code)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1160. Min Act: -0.0001
Data Index: 1031412 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1157. Min Act: -0.0001
Data Index: 1294584 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1153. Min Act: -0.0001
Data Index: 768761 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1062. Min Act: -0.0001
Data Index: 280979 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1083. Min Act: -0.0001
Data Index: 1162741 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1078. Min Act: -0.0001
Data Index: 204845 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1063. Min Act: -0.0001
Data Index: 1291890 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1010. Min Act: -0.0001
Data Index: 918330 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1055. Min Act: -0.0001
Data Index: 815991 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1043. Min Act: -0.0001
Data Index: 814309 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.0959. Min Act: -0.0001
Data Index: 898122 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.0977. Min Act: -0.0001
Data Index: 1060755 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1048. Min Act: -0.0001
Data Index: 14805 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1336. Min Range: -0.1336
Max Act: 0.1030. Min Act: -0.0001
Data Index: 870238 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19