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

Dataset: The Pile

Neuron 2783 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.4726. Min Act: -0.0000

Data Index: 256950 (The Pile)

Max Activating Token Index: 242

Text #1

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1306999 (The Pile)

Max Activating Token Index: 917

Text #2

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.2516. Min Act: -0.0000

Data Index: 176050 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1939. Min Act: -0.0000

Data Index: 1050996 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1696. Min Act: -0.0000

Data Index: 650563 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1455178 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1322446 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1934145 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1699. Min Act: -0.0000

Data Index: 117058 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1751. Min Act: -0.0000

Data Index: 179162 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1510. Min Act: -0.0000

Data Index: 816192 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1224386 (The Pile)

Max Activating Token Index: 732

Text #12

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1192. Min Act: -0.0000

Data Index: 386793 (The Pile)

Max Activating Token Index: 660

Text #13

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1037483 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.0702. Min Act: -0.0000

Data Index: 287457 (The Pile)

Max Activating Token Index: 856

Text #15

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1094133 (The Pile)

Max Activating Token Index: 75

Text #16

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1568. Min Act: -0.0000

Data Index: 1071688 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.0868. Min Act: -0.0001

Data Index: 1335191 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1523189 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 1.4726. Min Range: -1.4726

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1439497 (The Pile)

Max Activating Token Index: 448