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

Dataset: The Pile

Neuron 2800 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.2891. Min Act: -0.0000

Data Index: 1819373 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1017902 (The Pile)

Max Activating Token Index: 243

Text #2

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.2492. Min Act: -0.0000

Data Index: 649471 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1876630 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1204655 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1339966 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1150876 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.1205. Min Act: -0.0000

Data Index: 348952 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.1177. Min Act: -0.0000

Data Index: 821696 (The Pile)

Max Activating Token Index: 565

Text #9

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1302663 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.1448. Min Act: -0.0000

Data Index: 1597435 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0516. Min Act: -0.0000

Data Index: 724057 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0782. Min Act: -0.0000

Data Index: 509499 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0966. Min Act: -0.0000

Data Index: 1483551 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0272. Min Act: -0.0000

Data Index: 770897 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0384. Min Act: -0.0000

Data Index: 809185 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.9965. Min Act: -0.0000

Data Index: 620967 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1193739 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0534. Min Act: -0.0000

Data Index: 794631 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0312. Min Act: -0.0000

Data Index: 701712 (The Pile)

Max Activating Token Index: 747