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

Dataset: The Pile

Neuron 1459 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: 1.2897. Min Range: -1.2897

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1678459 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1834. Min Act: -0.0000

Data Index: 847114 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0758. Min Act: -0.0000

Data Index: 680188 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0738. Min Act: -0.0000

Data Index: 369211 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1943050 (The Pile)

Max Activating Token Index: 954

Text #5

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0402. Min Act: -0.0000

Data Index: 1240755 (The Pile)

Max Activating Token Index: 743

Text #6

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0506. Min Act: -0.0000

Data Index: 104279 (The Pile)

Max Activating Token Index: 84

Text #7

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1626667 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1297147 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0048. Min Act: -0.0000

Data Index: 734755 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1675858 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0346. Min Act: -0.0000

Data Index: 216058 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9526. Min Act: -0.0000

Data Index: 9286 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9276. Min Act: -0.0000

Data Index: 59501 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1713206 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1647481 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8547. Min Act: -0.0000

Data Index: 805438 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1918376 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9065. Min Act: -0.0000

Data Index: 190867 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1807744 (The Pile)

Max Activating Token Index: 682