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

Dataset: The Pile

Neuron 1508 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1529743 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.4254. Min Act: -0.0000

Data Index: 10062 (The Pile)

Max Activating Token Index: 973

Text #2

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1944691 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3639. Min Act: -0.0000

Data Index: 431929 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.4480. Min Act: -0.0000

Data Index: 1662609 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3168. Min Act: -0.0000

Data Index: 1601661 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1868110 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3205. Min Act: -0.0000

Data Index: 675479 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3341. Min Act: -0.0000

Data Index: 582488 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.2545. Min Act: -0.0000

Data Index: 1625006 (The Pile)

Max Activating Token Index: 992

Text #10

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.2480. Min Act: -0.0000

Data Index: 3054 (The Pile)

Max Activating Token Index: 770

Text #11

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.2483. Min Act: -0.0000

Data Index: 189839 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1098802 (The Pile)

Max Activating Token Index: 441

Text #13

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3122. Min Act: -0.0000

Data Index: 1170514 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.2139. Min Act: -0.0000

Data Index: 915877 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.2438. Min Act: -0.0000

Data Index: 934570 (The Pile)

Max Activating Token Index: 473

Text #16

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3502. Min Act: -0.0000

Data Index: 1108345 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1571970 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.3316. Min Act: -0.0000

Data Index: 874398 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 1.4978. Min Range: -1.4978

Max Act: 1.2398. Min Act: -0.0000

Data Index: 826510 (The Pile)

Max Activating Token Index: 521