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

Dataset: The Pile

Neuron 2005 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: 1.4952. Min Range: -1.4952

Max Act: 1.4743. Min Act: -0.0000

Data Index: 683747 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3917. Min Act: -0.0000

Data Index: 1069849 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4952. Min Act: -0.0000

Data Index: 936558 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1736953 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1647. Min Act: -0.0000

Data Index: 615879 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1634. Min Act: -0.0000

Data Index: 1196984 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1398. Min Act: -0.0000

Data Index: 878197 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.0332. Min Act: -0.0000

Data Index: 459397 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.0179. Min Act: -0.0000

Data Index: 426022 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1284. Min Act: -0.0000

Data Index: 1668972 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.0076. Min Act: -0.0000

Data Index: 802307 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1587802 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1045211 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1778185 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 1.4952. Min Range: -1.4952

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1501563 (The Pile)

Max Activating Token Index: 656

Text #15

Max Range: 1.4952. Min Range: -1.4952

Max Act: 0.8946. Min Act: -0.0000

Data Index: 319298 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 1.4952. Min Range: -1.4952

Max Act: 0.9678. Min Act: -0.0000

Data Index: 351056 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 1.4952. Min Range: -1.4952

Max Act: 0.9327. Min Act: -0.0000

Data Index: 441454 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 1.4952. Min Range: -1.4952

Max Act: 0.8054. Min Act: -0.0000

Data Index: 831370 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 1.4952. Min Range: -1.4952

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1434875 (The Pile)

Max Activating Token Index: 58