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

Dataset: The Pile

Neuron 4462 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.2523. Min Act: -0.0000

Data Index: 1165934 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.8061. Min Act: -0.0000

Data Index: 1311276 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.2020. Min Act: -0.0000

Data Index: 1132456 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.9573. Min Act: -0.0000

Data Index: 698251 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.8573. Min Act: -0.0000

Data Index: 1188759 (The Pile)

Max Activating Token Index: 391

Text #5

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.9994. Min Act: -0.0000

Data Index: 482274 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.8240. Min Act: -0.0000

Data Index: 914369 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.6827. Min Act: -0.0000

Data Index: 1733543 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.6304. Min Act: -0.0000

Data Index: 1687818 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.6356. Min Act: -0.0000

Data Index: 1925687 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.7148. Min Act: -0.0000

Data Index: 1393788 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.6673. Min Act: -0.0000

Data Index: 550805 (The Pile)

Max Activating Token Index: 161

Text #12

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.4937. Min Act: -0.0000

Data Index: 1964390 (The Pile)

Max Activating Token Index: 796

Text #13

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.5017. Min Act: -0.0000

Data Index: 906686 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.7964. Min Act: -0.0000

Data Index: 207943 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.4669. Min Act: -0.0000

Data Index: 795832 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.6487. Min Act: -0.0000

Data Index: 681803 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.6282. Min Act: -0.0000

Data Index: 1042454 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.5413. Min Act: -0.0000

Data Index: 503765 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 3.2523. Min Range: -3.2523

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1217365 (The Pile)

Max Activating Token Index: 651