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

Dataset: The Pile

Neuron 3494 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1951. Min Act: -0.0000

Data Index: 404720 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1722. Min Act: 0.0000

Data Index: 1312545 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1600. Min Act: 0.0000

Data Index: 45405 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1595. Min Act: 0.0001

Data Index: 1118554 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1533. Min Act: 0.0000

Data Index: 1856947 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1525. Min Act: 0.0000

Data Index: 1940951 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1526. Min Act: 0.0000

Data Index: 1084525 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1520. Min Act: 0.0001

Data Index: 1646653 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1501. Min Act: 0.0000

Data Index: 58770 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1470. Min Act: 0.0001

Data Index: 1422999 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1455. Min Act: 0.0000

Data Index: 216429 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1419. Min Act: 0.0000

Data Index: 1329719 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1413. Min Act: 0.0000

Data Index: 718860 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1395. Min Act: 0.0000

Data Index: 1289672 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1930461 (The Pile)

Max Activating Token Index: 4

Text #15

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1380. Min Act: 0.0000

Data Index: 522839 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1374. Min Act: 0.0000

Data Index: 457195 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1371. Min Act: 0.0000

Data Index: 688555 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1371. Min Act: 0.0000

Data Index: 332707 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1367. Min Act: 0.0000

Data Index: 616293 (The Pile)

Max Activating Token Index: 1023