Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1659 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.5544. Min Act: -0.0000

Data Index: 387055 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.2300. Min Act: -0.0000

Data Index: 242559 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.2482. Min Act: -0.0000

Data Index: 863168 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.0999. Min Act: -0.0000

Data Index: 484560 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1302500 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1124520 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.1497. Min Act: -0.0000

Data Index: 958555 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.1017. Min Act: -0.0000

Data Index: 851561 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.0657. Min Act: -0.0000

Data Index: 458652 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.0877. Min Act: -0.0000

Data Index: 582143 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9541. Min Act: -0.0000

Data Index: 707625 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1618559 (Python Code)

Max Activating Token Index: 685

Text #12

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9682. Min Act: -0.0000

Data Index: 476530 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9710. Min Act: -0.0000

Data Index: 314606 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1135562 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9061. Min Act: -0.0000

Data Index: 783552 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9436. Min Act: -0.0000

Data Index: 946077 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9094. Min Act: -0.0000

Data Index: 382853 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1112690 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.5544. Min Range: -1.5544

Max Act: 0.9023. Min Act: -0.0000

Data Index: 430329 (C4 (Web Text))

Max Activating Token Index: 621