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

Dataset: The Pile

Neuron 3194 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: 0.2395. Min Range: -0.2395

Max Act: 0.2395. Min Act: -0.0000

Data Index: 293367 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2019. Min Act: -0.0000

Data Index: 471940 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1865080 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2005. Min Act: -0.0000

Data Index: 157439 (The Pile)

Max Activating Token Index: 708

Text #4

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1104879 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1779. Min Act: -0.0000

Data Index: 476582 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1688. Min Act: -0.0000

Data Index: 406926 (The Pile)

Max Activating Token Index: 35

Text #7

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1330500 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1553451 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1768. Min Act: -0.0000

Data Index: 720806 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1683. Min Act: -0.0000

Data Index: 465843 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1774. Min Act: -0.0000

Data Index: 425380 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1700. Min Act: -0.0000

Data Index: 497126 (The Pile)

Max Activating Token Index: 801

Text #13

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1662. Min Act: -0.0000

Data Index: 96593 (The Pile)

Max Activating Token Index: 497

Text #14

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1402. Min Act: -0.0000

Data Index: 186467 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1554. Min Act: -0.0000

Data Index: 465396 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1685027 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1351567 (The Pile)

Max Activating Token Index: 509

Text #18

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1838198 (The Pile)

Max Activating Token Index: 317

Text #19

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1392685 (The Pile)

Max Activating Token Index: 378