Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4760 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.8561. Min Act: -0.0000

Data Index: 872351 (The Pile)

Max Activating Token Index: 896

Text #1

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.9266. Min Act: -0.0000

Data Index: 965579 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.8282. Min Act: -0.0000

Data Index: 746109 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.8198. Min Act: -0.0000

Data Index: 310619 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1723372 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7673. Min Act: -0.0000

Data Index: 255889 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1754052 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.8250. Min Act: -0.0000

Data Index: 360544 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1910955 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.8453. Min Act: -0.0000

Data Index: 909616 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7658. Min Act: -0.0000

Data Index: 254279 (The Pile)

Max Activating Token Index: 643

Text #11

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7480. Min Act: -0.0000

Data Index: 531447 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7352. Min Act: -0.0000

Data Index: 564589 (The Pile)

Max Activating Token Index: 358

Text #13

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7826. Min Act: -0.0000

Data Index: 880470 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1081038 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.6945. Min Act: -0.0000

Data Index: 272407 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7380. Min Act: -0.0000

Data Index: 572378 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1339192 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7007. Min Act: -0.0000

Data Index: 527492 (The Pile)

Max Activating Token Index: 481

Text #19

Max Range: 0.9266. Min Range: -0.9266

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1578167 (The Pile)

Max Activating Token Index: 111