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

Dataset: The Pile

Neuron 391 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0427. Min Range: -1.0427

Max Act: 1.0427. Min Act: -0.0000

Data Index: 227388 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9844. Min Act: -0.0000

Data Index: 988342 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9802. Min Act: -0.0000

Data Index: 289459 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1696679 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 1.0427. Min Range: -1.0427

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1247567 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 1.0427. Min Range: -1.0427

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1838168 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9721. Min Act: -0.0000

Data Index: 633751 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9597. Min Act: -0.0000

Data Index: 950858 (The Pile)

Max Activating Token Index: 439

Text #8

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9655. Min Act: -0.0000

Data Index: 675213 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9319. Min Act: -0.0000

Data Index: 639460 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9162. Min Act: -0.0000

Data Index: 575418 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1771810 (The Pile)

Max Activating Token Index: 585

Text #12

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9606. Min Act: -0.0000

Data Index: 953615 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9370. Min Act: -0.0000

Data Index: 776602 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9243. Min Act: -0.0000

Data Index: 554574 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1601648 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1325306 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9135. Min Act: -0.0000

Data Index: 148182 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1954288 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9152. Min Act: -0.0000

Data Index: 941352 (The Pile)

Max Activating Token Index: 176