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

Dataset: The Pile

Neuron 2923 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1478. Min Act: -0.0000

Data Index: 697111 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1457065 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1697434 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1167. Min Act: -0.0000

Data Index: 417157 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0973. Min Act: -0.0000

Data Index: 802878 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1051. Min Act: -0.0000

Data Index: 644033 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1184721 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0935. Min Act: -0.0000

Data Index: 313171 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1615352 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0928. Min Act: -0.0000

Data Index: 872680 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1183173 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1722833 (The Pile)

Max Activating Token Index: 321

Text #12

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0839. Min Act: -0.0000

Data Index: 113571 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0812. Min Act: -0.0000

Data Index: 397716 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1792204 (The Pile)

Max Activating Token Index: 904

Text #15

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0724. Min Act: -0.0000

Data Index: 919599 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1966795 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1959900 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0774. Min Act: -0.0000

Data Index: 162171 (The Pile)

Max Activating Token Index: 324

Text #19

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0767. Min Act: -0.0000

Data Index: 220757 (The Pile)

Max Activating Token Index: 508