Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 759 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1818. Min Act: -0.0001

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1508. Min Act: -0.0001

Data Index: 105244 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1328977 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1496. Min Act: -0.0001

Data Index: 393069 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1575. Min Act: -0.0001

Data Index: 277995 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1455. Min Act: -0.0001

Data Index: 607318 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1531. Min Act: -0.0001

Data Index: 592539 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1279. Min Act: -0.0001

Data Index: 230017 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1301100 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1074929 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1324228 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1228644 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1293. Min Act: -0.0001

Data Index: 255627 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1282. Min Act: -0.0001

Data Index: 139510 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1358. Min Act: -0.0001

Data Index: 466275 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1357. Min Act: -0.0001

Data Index: 246666 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1141423 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1297. Min Act: -0.0001

Data Index: 255672 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1097210 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1318385 (C4 (Web Text))

Max Activating Token Index: 492