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

Dataset: The Pile

Neuron 3081 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: 0.2592. Min Range: -0.2592

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1583184 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1386375 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1569456 (The Pile)

Max Activating Token Index: 519

Text #3

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1983309 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1351777 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1599. Min Act: -0.0000

Data Index: 417939 (The Pile)

Max Activating Token Index: 902

Text #6

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1503. Min Act: -0.0000

Data Index: 571583 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1737429 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1422. Min Act: -0.0000

Data Index: 761520 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1185874 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1511804 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1149187 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1240657 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1186526 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1702125 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1377. Min Act: -0.0000

Data Index: 28165 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1568192 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1389. Min Act: -0.0000

Data Index: 757618 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1202. Min Act: -0.0000

Data Index: 75665 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1859739 (The Pile)

Max Activating Token Index: 818