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

Dataset: The Pile

Neuron 720 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1524436 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.1831. Min Act: -0.0000

Data Index: 630627 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.1048. Min Act: -0.0000

Data Index: 645617 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.1439. Min Act: -0.0000

Data Index: 1166435 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1578836 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1006398 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.0190. Min Act: -0.0000

Data Index: 110439 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1202635 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9505. Min Act: -0.0000

Data Index: 39941 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1703759 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.8778. Min Act: -0.0000

Data Index: 96835 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1700400 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9470. Min Act: -0.0000

Data Index: 965053 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1551199 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9509. Min Act: -0.0000

Data Index: 967064 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9371. Min Act: -0.0000

Data Index: 943840 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1774290 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9330. Min Act: -0.0000

Data Index: 450443 (The Pile)

Max Activating Token Index: 32

Text #18

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1347342 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.9482. Min Act: -0.0000

Data Index: 556960 (The Pile)

Max Activating Token Index: 85