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

Dataset: The Pile

Neuron 2439 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1862676 (The Pile)

Max Activating Token Index: 474

Text #1

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1736322 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1079435 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1870691 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2200. Min Act: -0.0000

Data Index: 538554 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1520019 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1880. Min Act: -0.0000

Data Index: 686889 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1311244 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1629. Min Act: -0.0000

Data Index: 310121 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1863145 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1738. Min Act: -0.0000

Data Index: 601241 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1292518 (The Pile)

Max Activating Token Index: 132

Text #12

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1966324 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1600. Min Act: -0.0000

Data Index: 2262 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1703. Min Act: -0.0000

Data Index: 38763 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1540618 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1531. Min Act: -0.0000

Data Index: 390717 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1352526 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1470. Min Act: -0.0000

Data Index: 924274 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1413. Min Act: -0.0000

Data Index: 506445 (The Pile)

Max Activating Token Index: 39