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

Dataset: The Pile

Neuron 4698 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: 1.4205. Min Range: -1.4205

Max Act: 1.4205. Min Act: -0.0000

Data Index: 1475122 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.2600. Min Act: -0.0000

Data Index: 330377 (The Pile)

Max Activating Token Index: 75

Text #2

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.1972. Min Act: -0.0000

Data Index: 743658 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1199555 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1214354 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1343861 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.1709. Min Act: -0.0000

Data Index: 1890937 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0840. Min Act: -0.0000

Data Index: 426719 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.1059. Min Act: -0.0000

Data Index: 466867 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.2122. Min Act: -0.0000

Data Index: 301006 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1315803 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.1199. Min Act: -0.0000

Data Index: 646253 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0784. Min Act: -0.0000

Data Index: 34237 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1134005 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.1397. Min Act: -0.0000

Data Index: 762828 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1671135 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1750122 (The Pile)

Max Activating Token Index: 30

Text #17

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0022. Min Act: -0.0000

Data Index: 917063 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0239. Min Act: -0.0000

Data Index: 420663 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1711221 (The Pile)

Max Activating Token Index: 39