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

Dataset: The Pile

Neuron 4969 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: 1.8204. Min Range: -1.8204

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1313761 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.8204. Min Act: -0.0000

Data Index: 948066 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.7793. Min Act: -0.0000

Data Index: 1789169 (The Pile)

Max Activating Token Index: 423

Text #3

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.5347. Min Act: -0.0000

Data Index: 533844 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1572628 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1205170 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.2971. Min Act: -0.0000

Data Index: 1438940 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1548772 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.1685. Min Act: -0.0000

Data Index: 1472925 (The Pile)

Max Activating Token Index: 577

Text #9

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1232534 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.3011. Min Act: 0.0000

Data Index: 1619997 (The Pile)

Max Activating Token Index: 119

Text #11

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.1619. Min Act: -0.0000

Data Index: 771055 (The Pile)

Max Activating Token Index: 748

Text #12

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.2434. Min Act: -0.0000

Data Index: 714526 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1415328 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.3185. Min Act: -0.0000

Data Index: 615650 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.0645. Min Act: -0.0000

Data Index: 1434829 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1849045 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 1.8204. Min Range: -1.8204

Max Act: 0.9635. Min Act: -0.0000

Data Index: 270824 (The Pile)

Max Activating Token Index: 611

Text #18

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.1098. Min Act: -0.0000

Data Index: 767901 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 1.8204. Min Range: -1.8204

Max Act: 1.0252. Min Act: -0.0000

Data Index: 453147 (The Pile)

Max Activating Token Index: 855