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

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

Neuron 3770 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: 0.1549. Min Range: -0.1549

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1554054 (Python Code)

Max Activating Token Index: 766

Text #1

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1055929 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1620012 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1270. Min Act: -0.0000

Data Index: 91098 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1269. Min Act: -0.0000

Data Index: 202563 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1227. Min Act: -0.0000

Data Index: 848400 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1621576 (Python Code)

Max Activating Token Index: 150

Text #7

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1178. Min Act: -0.0000

Data Index: 278141 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1148. Min Act: -0.0000

Data Index: 681329 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1212. Min Act: -0.0000

Data Index: 896631 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1320981 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1557562 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1143. Min Act: -0.0000

Data Index: 943311 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1157. Min Act: -0.0000

Data Index: 828498 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1065. Min Act: -0.0000

Data Index: 417592 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1094. Min Act: -0.0000

Data Index: 538161 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1080. Min Act: -0.0000

Data Index: 92547 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1532739 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1137. Min Act: -0.0000

Data Index: 628035 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1454635 (Python Code)

Max Activating Token Index: 42