Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1118 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0002

Data Index: 691906 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1005616 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1251. Min Act: -0.0001

Data Index: 387896 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1256. Min Act: -0.0002

Data Index: 1144821 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1237. Min Act: -0.0002

Data Index: 331437 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1150. Min Act: -0.0002

Data Index: 835997 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1204. Min Act: -0.0002

Data Index: 262333 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1233. Min Act: -0.0002

Data Index: 863911 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1150. Min Act: -0.0002

Data Index: 995613 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1024317 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1146. Min Act: -0.0002

Data Index: 80440 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1136. Min Act: -0.0002

Data Index: 432431 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1197563 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1219494 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1119. Min Act: -0.0002

Data Index: 120698 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1116. Min Act: -0.0001

Data Index: 87240 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1111. Min Act: -0.0002

Data Index: 406880 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1112. Min Act: -0.0002

Data Index: 317651 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1149. Min Act: -0.0002

Data Index: 410817 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1073. Min Act: -0.0002

Data Index: 94279 (C4 (Web Text))

Max Activating Token Index: 611