Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 111 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1400515 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1158898 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1854. Min Act: 0.0000

Data Index: 950300 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1689849 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1663. Min Act: -0.0000

Data Index: 167042 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1612. Min Act: 0.0000

Data Index: 76445 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1605604 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1362554 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1519. Min Act: -0.0000

Data Index: 124095 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1544. Min Act: -0.0000

Data Index: 112508 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1513. Min Act: 0.0001

Data Index: 81454 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1468. Min Act: 0.0000

Data Index: 1806714 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1304. Min Act: -0.0001

Data Index: 216242 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1619207 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1386. Min Act: 0.0000

Data Index: 442451 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1792437 (The Pile)

Max Activating Token Index: 244

Text #16

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1571942 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1488657 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1385. Min Act: 0.0000

Data Index: 1801004 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1325. Min Act: -0.0000

Data Index: 349269 (The Pile)

Max Activating Token Index: 680