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

Dataset: The Pile

Neuron 4005 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: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: 0.0000

Data Index: 1295616 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1667. Min Act: -0.0000

Data Index: 914599 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1591. Min Act: 0.0000

Data Index: 178058 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1499. Min Act: -0.0000

Data Index: 580454 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1391. Min Act: 0.0000

Data Index: 212102 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1377. Min Act: 0.0000

Data Index: 790365 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1352. Min Act: 0.0000

Data Index: 470670 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1170338 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1344. Min Act: -0.0000

Data Index: 516645 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1324. Min Act: -0.0000

Data Index: 647553 (The Pile)

Max Activating Token Index: 5

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1325. Min Act: 0.0000

Data Index: 150175 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1311. Min Act: 0.0000

Data Index: 1356488 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1309. Min Act: 0.0000

Data Index: 630488 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1286. Min Act: 0.0000

Data Index: 1033987 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1279. Min Act: 0.0000

Data Index: 226999 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1686709 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1258. Min Act: 0.0000

Data Index: 570594 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1253. Min Act: 0.0000

Data Index: 138931 (The Pile)

Max Activating Token Index: 70

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1254. Min Act: -0.0000

Data Index: 141805 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1251. Min Act: 0.0000

Data Index: 1789883 (The Pile)

Max Activating Token Index: 212