Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1690 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.7016. Min Act: -0.0000

Data Index: 56740 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.2212. Min Act: -0.0000

Data Index: 1288204 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.4221. Min Act: -0.0000

Data Index: 1169982 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.1855. Min Act: -0.0000

Data Index: 559311 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.1445. Min Act: -0.0000

Data Index: 1312528 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.2053. Min Act: -0.0000

Data Index: 1348525 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.1992. Min Act: -0.0000

Data Index: 1106784 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.0815. Min Act: -0.0000

Data Index: 846941 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.1269. Min Act: -0.0000

Data Index: 411339 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.1048. Min Act: -0.0000

Data Index: 398597 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.1443. Min Act: -0.0000

Data Index: 60094 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.0650. Min Act: -0.0000

Data Index: 617476 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.1603. Min Act: -0.0000

Data Index: 135031 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.0056. Min Act: -0.0000

Data Index: 1105007 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.0865. Min Act: -0.0000

Data Index: 1342924 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 2.7016. Min Range: -2.7016

Max Act: 1.9023. Min Act: -0.0000

Data Index: 1147930 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.0806. Min Act: -0.0000

Data Index: 1202398 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.0318. Min Act: -0.0000

Data Index: 553950 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.0088. Min Act: -0.0000

Data Index: 1203738 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 2.7016. Min Range: -2.7016

Max Act: 1.9605. Min Act: -0.0000

Data Index: 719314 (C4 (Web Text))

Max Activating Token Index: 942