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

Dataset: The Pile

Neuron 1606 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.3560. Min Act: -0.0000

Data Index: 1463391 (The Pile)

Max Activating Token Index: 279

Text #1

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.4012. Min Act: -0.0000

Data Index: 125354 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1545575 (The Pile)

Max Activating Token Index: 149

Text #3

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1854332 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1543511 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.1924. Min Act: -0.0000

Data Index: 722736 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.1348. Min Act: -0.0000

Data Index: 666063 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1630825 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.3413. Min Act: -0.0000

Data Index: 1416548 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.1212. Min Act: -0.0000

Data Index: 310387 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.0262. Min Act: -0.0000

Data Index: 44283 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.0990. Min Act: -0.0000

Data Index: 1834763 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.1810. Min Act: -0.0000

Data Index: 159141 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1276860 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1207604 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.0325. Min Act: -0.0000

Data Index: 910761 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.0779. Min Act: -0.0000

Data Index: 418479 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1495099 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1664562 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 1.4012. Min Range: -1.4012

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1410368 (The Pile)

Max Activating Token Index: 817