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

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

Neuron 3516 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1409. Min Act: -0.0002

Data Index: 1080103 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1455. Min Act: -0.0002

Data Index: 536388 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1347. Min Act: -0.0002

Data Index: 865407 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1426. Min Act: -0.0002

Data Index: 338485 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1272. Min Act: -0.0002

Data Index: 765446 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1200. Min Act: -0.0002

Data Index: 168149 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1218. Min Act: -0.0002

Data Index: 423931 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1267. Min Act: -0.0002

Data Index: 190279 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1418. Min Act: -0.0002

Data Index: 32399 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1133. Min Act: -0.0002

Data Index: 615700 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1256. Min Act: -0.0002

Data Index: 684691 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1213. Min Act: -0.0002

Data Index: 634832 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1123. Min Act: -0.0002

Data Index: 268940 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1112. Min Act: -0.0002

Data Index: 709788 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1065. Min Act: -0.0002

Data Index: 451655 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1253907 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1130. Min Act: -0.0002

Data Index: 685007 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1142785 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1077. Min Act: -0.0002

Data Index: 323392 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1104. Min Act: -0.0002

Data Index: 635065 (C4 (Web Text))

Max Activating Token Index: 293