Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2110 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.0444. Min Range: -5.0444

Max Act: 5.0444. Min Act: -0.0000

Data Index: 1048221 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 5.0444. Min Range: -5.0444

Max Act: 4.6047. Min Act: -0.0000

Data Index: 1197946 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 5.0444. Min Range: -5.0444

Max Act: 4.3196. Min Act: -0.0000

Data Index: 788727 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 5.0444. Min Range: -5.0444

Max Act: 4.4448. Min Act: -0.0000

Data Index: 222281 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 5.0444. Min Range: -5.0444

Max Act: 4.4987. Min Act: -0.0000

Data Index: 1158625 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 5.0444. Min Range: -5.0444

Max Act: 4.8209. Min Act: -0.0000

Data Index: 866167 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 5.0444. Min Range: -5.0444

Max Act: 4.0588. Min Act: -0.0000

Data Index: 476335 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 5.0444. Min Range: -5.0444

Max Act: 4.0993. Min Act: -0.0000

Data Index: 221099 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 5.0444. Min Range: -5.0444

Max Act: 4.1849. Min Act: -0.0000

Data Index: 1324468 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 5.0444. Min Range: -5.0444

Max Act: 3.7572. Min Act: -0.0000

Data Index: 290824 (The Pile)

Max Activating Token Index: 196

Text #10

Max Range: 5.0444. Min Range: -5.0444

Max Act: 3.5426. Min Act: -0.0000

Data Index: 499742 (The Pile)

Max Activating Token Index: 426

Text #11

Max Range: 5.0444. Min Range: -5.0444

Max Act: 3.6375. Min Act: -0.0000

Data Index: 733136 (The Pile)

Max Activating Token Index: 349

Text #12

Max Range: 5.0444. Min Range: -5.0444

Max Act: 3.2348. Min Act: -0.0000

Data Index: 168572 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 5.0444. Min Range: -5.0444

Max Act: 3.2101. Min Act: -0.0000

Data Index: 932337 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 5.0444. Min Range: -5.0444

Max Act: 3.0079. Min Act: -0.0000

Data Index: 971725 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 5.0444. Min Range: -5.0444

Max Act: 2.6969. Min Act: -0.0000

Data Index: 407331 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 5.0444. Min Range: -5.0444

Max Act: 2.7658. Min Act: -0.0000

Data Index: 1165699 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 5.0444. Min Range: -5.0444

Max Act: 2.9923. Min Act: 0.0000

Data Index: 1756331 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 5.0444. Min Range: -5.0444

Max Act: 2.5126. Min Act: -0.0000

Data Index: 306752 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 5.0444. Min Range: -5.0444

Max Act: 2.5199. Min Act: 0.0000

Data Index: 1633670 (The Pile)

Max Activating Token Index: 873