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

Dataset: The Pile

Neuron 2262 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: 1.4495. Min Range: -1.4495

Max Act: 1.4495. Min Act: -0.0000

Data Index: 184807 (The Pile)

Max Activating Token Index: 921

Text #1

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.3992. Min Act: -0.0000

Data Index: 337307 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.2304. Min Act: -0.0000

Data Index: 1795376 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1096902 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1528553 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.2871. Min Act: -0.0000

Data Index: 865004 (The Pile)

Max Activating Token Index: 652

Text #6

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1743. Min Act: -0.0000

Data Index: 1402437 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1086021 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1821613 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1641527 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 1.4495. Min Range: -1.4495

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1393768 (The Pile)

Max Activating Token Index: 434

Text #11

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0657. Min Act: -0.0000

Data Index: 638773 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 1.4495. Min Range: -1.4495

Max Act: 0.9741. Min Act: -0.0000

Data Index: 406977 (The Pile)

Max Activating Token Index: 225

Text #13

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0933. Min Act: -0.0000

Data Index: 711911 (The Pile)

Max Activating Token Index: 241

Text #14

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0730. Min Act: -0.0000

Data Index: 159526 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1844390 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0172. Min Act: -0.0000

Data Index: 517899 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0623. Min Act: -0.0000

Data Index: 1317651 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0809. Min Act: -0.0000

Data Index: 974067 (The Pile)

Max Activating Token Index: 410

Text #19

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0234. Min Act: -0.0000

Data Index: 637806 (The Pile)

Max Activating Token Index: 925