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

Dataset: The Pile

Neuron 2516 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: 1.6271. Min Range: -1.6271

Max Act: 1.6271. Min Act: -0.0000

Data Index: 1234990 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.4243. Min Act: -0.0000

Data Index: 1138482 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.3746. Min Act: -0.0000

Data Index: 276611 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.5021. Min Act: -0.0000

Data Index: 596043 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.2550. Min Act: -0.0000

Data Index: 1788813 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.3728. Min Act: -0.0000

Data Index: 1347707 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.2255. Min Act: -0.0000

Data Index: 266833 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.2745. Min Act: -0.0000

Data Index: 459280 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.1328. Min Act: -0.0000

Data Index: 1453528 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.2545. Min Act: -0.0000

Data Index: 1380804 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.2477. Min Act: -0.0000

Data Index: 250518 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.2345. Min Act: -0.0000

Data Index: 1171088 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1909939 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1383136 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.3135. Min Act: -0.0000

Data Index: 321630 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.1689. Min Act: -0.0000

Data Index: 976465 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.2183. Min Act: -0.0000

Data Index: 78110 (The Pile)

Max Activating Token Index: 570

Text #17

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.2222. Min Act: -0.0000

Data Index: 1631820 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.1566. Min Act: 0.0000

Data Index: 497251 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 1.6271. Min Range: -1.6271

Max Act: 1.1602. Min Act: -0.0000

Data Index: 969511 (The Pile)

Max Activating Token Index: 243