Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2291 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0001

Data Index: 242234 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0484. Min Act: -0.0001

Data Index: 702980 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0451. Min Act: -0.0001

Data Index: 838999 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1644415 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0419. Min Act: -0.0000

Data Index: 154930 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0396. Min Act: -0.0000

Data Index: 710479 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0358. Min Act: -0.0000

Data Index: 1168946 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0406. Min Act: -0.0001

Data Index: 642577 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1052739 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1319548 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1141915 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1150858 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0377. Min Act: -0.0001

Data Index: 391762 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0368. Min Act: -0.0001

Data Index: 556456 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1384977 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1494086 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0380. Min Act: -0.0001

Data Index: 1215151 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0394. Min Act: -0.0001

Data Index: 747428 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1004357 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0347. Min Act: -0.0000

Data Index: 873611 (C4 (Web Text))

Max Activating Token Index: 458