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

Dataset: The Pile

Neuron 5 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: 0.3381. Min Range: -0.3381

Max Act: 0.3381. Min Act: -0.0000

Data Index: 112170 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.3210. Min Act: -0.0000

Data Index: 687652 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1345743 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2705. Min Act: -0.0000

Data Index: 290808 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1833359 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1215798 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1302202 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1705889 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1671347 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2383. Min Act: -0.0000

Data Index: 510632 (The Pile)

Max Activating Token Index: 872

Text #10

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1705901 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1600327 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2095. Min Act: -0.0000

Data Index: 524856 (The Pile)

Max Activating Token Index: 755

Text #13

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2101. Min Act: -0.0000

Data Index: 50814 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1048168 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2040. Min Act: -0.0000

Data Index: 976546 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1518510 (The Pile)

Max Activating Token Index: 711

Text #17

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2174. Min Act: -0.0000

Data Index: 128646 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2008. Min Act: -0.0000

Data Index: 123459 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1842703 (The Pile)

Max Activating Token Index: 664