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

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

Neuron 43 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: 0.1594. Min Range: -0.1594

Max Act: 0.1594. Min Act: -0.0002

Data Index: 483539 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1525. Min Act: -0.0002

Data Index: 321864 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1530. Min Act: -0.0002

Data Index: 1117509 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1469. Min Act: -0.0002

Data Index: 197163 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1118754 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1498. Min Act: -0.0002

Data Index: 476260 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1187406 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1417. Min Act: -0.0002

Data Index: 1358213 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1448. Min Act: -0.0002

Data Index: 294184 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1415. Min Act: -0.0002

Data Index: 232245 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1342. Min Act: -0.0002

Data Index: 1287569 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1369. Min Act: -0.0002

Data Index: 660378 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1369. Min Act: -0.0002

Data Index: 241975 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1173110 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1333. Min Act: -0.0002

Data Index: 253333 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1238054 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1279. Min Act: -0.0001

Data Index: 495229 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1309. Min Act: -0.0002

Data Index: 326204 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1358. Min Act: -0.0002

Data Index: 654883 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1310. Min Act: -0.0002

Data Index: 1327945 (C4 (Web Text))

Max Activating Token Index: 258