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

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

Neuron 229 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.2272. Min Act: -0.0001

Data Index: 423454 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1528. Min Act: -0.0001

Data Index: 57898 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1500. Min Act: -0.0002

Data Index: 933953 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1403. Min Act: -0.0001

Data Index: 782959 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1297. Min Act: -0.0001

Data Index: 197064 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1584. Min Act: -0.0001

Data Index: 911622 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.0952. Min Act: -0.0001

Data Index: 101925 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1430. Min Act: -0.0001

Data Index: 259751 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1010877 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1305581 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1310529 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1100. Min Act: -0.0001

Data Index: 291157 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1078. Min Act: -0.0001

Data Index: 892215 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1131. Min Act: -0.0001

Data Index: 589411 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1101729 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1324. Min Act: -0.0001

Data Index: 844521 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1138. Min Act: -0.0001

Data Index: 763663 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1077. Min Act: -0.0001

Data Index: 988036 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1045. Min Act: -0.0001

Data Index: 829522 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1130. Min Act: -0.0002

Data Index: 78025 (C4 (Web Text))

Max Activating Token Index: 178