Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 264 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1120177 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1250055 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0451. Min Act: -0.0000

Data Index: 543734 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0433. Min Act: -0.0000

Data Index: 1642573 (Python Code)

Max Activating Token Index: 198

Text #4

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0428. Min Act: -0.0000

Data Index: 1012024 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0406. Min Act: -0.0000

Data Index: 310570 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1421597 (Python Code)

Max Activating Token Index: 560

Text #7

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1079967 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1290863 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0429. Min Act: -0.0000

Data Index: 1208647 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0408. Min Act: -0.0000

Data Index: 966684 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0404. Min Act: -0.0001

Data Index: 3475 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0391. Min Act: -0.0001

Data Index: 729026 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0381. Min Act: -0.0000

Data Index: 616764 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1008673 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1639502 (Python Code)

Max Activating Token Index: 692

Text #16

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0383. Min Act: -0.0001

Data Index: 936715 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0397. Min Act: -0.0001

Data Index: 722910 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1258820 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1001777 (C4 (Web Text))

Max Activating Token Index: 511