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

Dataset: The Pile

Neuron 3522 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.2260. Min Act: -0.0000

Data Index: 10577 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.2021. Min Act: -0.0000

Data Index: 148563 (The Pile)

Max Activating Token Index: 784

Text #2

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1822. Min Act: -0.0000

Data Index: 28593 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1706. Min Act: -0.0000

Data Index: 554760 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1178727 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1817230 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1560757 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1584. Min Act: -0.0000

Data Index: 969114 (The Pile)

Max Activating Token Index: 410

Text #8

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1817965 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1522845 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1354. Min Act: -0.0000

Data Index: 108602 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1233054 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1634752 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1395. Min Act: -0.0000

Data Index: 20919 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1407. Min Act: -0.0000

Data Index: 592583 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1521898 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1613716 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1337. Min Act: -0.0000

Data Index: 901392 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1248. Min Act: -0.0000

Data Index: 630704 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1188. Min Act: -0.0000

Data Index: 761553 (The Pile)

Max Activating Token Index: 772