Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3953 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1641. Min Act: -0.0001
Data Index: 484 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1516. Min Act: -0.0001
Data Index: 1256523 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1419. Min Act: -0.0001
Data Index: 858259 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1306. Min Act: -0.0001
Data Index: 1036833 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1334. Min Act: -0.0001
Data Index: 603857 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1144. Min Act: -0.0001
Data Index: 972768 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1089. Min Act: -0.0001
Data Index: 1269232 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1118. Min Act: -0.0001
Data Index: 776 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1035. Min Act: -0.0001
Data Index: 202815 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1065. Min Act: -0.0001
Data Index: 1593128 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1134. Min Act: -0.0001
Data Index: 1161288 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1036. Min Act: -0.0001
Data Index: 491805 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.0923. Min Act: -0.0001
Data Index: 325950 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1090. Min Act: -0.0001
Data Index: 602850 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1148. Min Act: -0.0001
Data Index: 1544909 (Python Code)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.0964. Min Act: -0.0001
Data Index: 520659 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.1020. Min Act: -0.0001
Data Index: 968567 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.0981. Min Act: -0.0001
Data Index: 321726 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.0924. Min Act: -0.0001
Data Index: 936432 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1641. Min Range: -0.1641
Max Act: 0.0876. Min Act: -0.0001
Data Index: 1444923 (Python Code)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19