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

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

Neuron 1155 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: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0002

Data Index: 350012 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1452. Min Act: -0.0002

Data Index: 682614 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1402. Min Act: -0.0002

Data Index: 646763 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1350. Min Act: -0.0002

Data Index: 160471 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1332. Min Act: -0.0002

Data Index: 206760 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1257. Min Act: -0.0001

Data Index: 718505 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1271. Min Act: -0.0002

Data Index: 931527 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1310171 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1248. Min Act: -0.0002

Data Index: 534733 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1178. Min Act: -0.0002

Data Index: 989728 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1203. Min Act: -0.0002

Data Index: 546279 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1026207 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1219. Min Act: -0.0001

Data Index: 48185 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1205. Min Act: -0.0002

Data Index: 925881 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1205. Min Act: -0.0002

Data Index: 445210 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1209. Min Act: -0.0002

Data Index: 710570 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1200. Min Act: -0.0002

Data Index: 153369 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1047265 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1175. Min Act: -0.0002

Data Index: 920524 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1279732 (C4 (Web Text))

Max Activating Token Index: 871