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

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

Neuron 4783 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: 0.1696. Min Range: -0.1696

Max Act: 0.1696. Min Act: -0.0000

Data Index: 717584 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1594. Min Act: -0.0000

Data Index: 272179 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1171107 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1376. Min Act: -0.0000

Data Index: 370343 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1419. Min Act: -0.0000

Data Index: 566841 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1353. Min Act: -0.0000

Data Index: 278078 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1422. Min Act: -0.0000

Data Index: 757844 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1307. Min Act: -0.0000

Data Index: 383393 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1235. Min Act: -0.0000

Data Index: 27857 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1051641 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1189. Min Act: -0.0000

Data Index: 203617 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1244. Min Act: -0.0000

Data Index: 963354 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1168. Min Act: -0.0000

Data Index: 518700 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1246. Min Act: -0.0000

Data Index: 416320 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1141. Min Act: -0.0000

Data Index: 342096 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1183. Min Act: -0.0000

Data Index: 126812 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1034699 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1162. Min Act: -0.0000

Data Index: 713507 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1138355 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1112. Min Act: -0.0000

Data Index: 130159 (C4 (Web Text))

Max Activating Token Index: 842