Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1028 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0490. Min Act: -0.0003

Data Index: 455206 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0003

Data Index: 868836 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1143844 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0481. Min Act: -0.0003

Data Index: 597782 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0474. Min Act: -0.0003

Data Index: 613366 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0462. Min Act: -0.0003

Data Index: 701540 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0456. Min Act: -0.0002

Data Index: 522184 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1244551 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0450. Min Act: -0.0003

Data Index: 878892 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1223747 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0447. Min Act: -0.0003

Data Index: 206623 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1378658 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0436. Min Act: -0.0003

Data Index: 800987 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1237091 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0430. Min Act: -0.0004

Data Index: 1302102 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0429. Min Act: -0.0003

Data Index: 237218 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1505406 (Python Code)

Max Activating Token Index: 238

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0425. Min Act: -0.0004

Data Index: 276804 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1161765 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0421. Min Act: -0.0003

Data Index: 747458 (C4 (Web Text))

Max Activating Token Index: 390