Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 172 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.8049. Min Range: -5.8049

Max Act: 5.0132. Min Act: -0.0000

Data Index: 1094987 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 5.8049. Min Range: -5.8049

Max Act: 5.8049. Min Act: -0.0000

Data Index: 821938 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1328738 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.2425. Min Act: -0.0000

Data Index: 816826 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1174348 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1095941 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1283019 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.2172. Min Act: -0.0000

Data Index: 974640 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1660. Min Act: -0.0000

Data Index: 8272 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1193809 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1028940 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1846. Min Act: -0.0000

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1741. Min Act: -0.0000

Data Index: 193986 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1291402 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1728. Min Act: -0.0000

Data Index: 184798 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1085683 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.0817. Min Act: -0.0000

Data Index: 72179 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1670. Min Act: -0.0000

Data Index: 681681 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1615. Min Act: -0.0000

Data Index: 386989 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 5.8049. Min Range: -5.8049

Max Act: 0.1707. Min Act: -0.0000

Data Index: 140873 (C4 (Web Text))

Max Activating Token Index: 24