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

Dataset: The Pile

Neuron 3102 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: 3.7952. Min Range: -3.7952

Max Act: 3.4487. Min Act: -0.0000

Data Index: 1710562 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.7649. Min Act: -0.0000

Data Index: 727729 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.7952. Min Act: -0.0000

Data Index: 407549 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.7506. Min Act: -0.0000

Data Index: 1076864 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.5750. Min Act: -0.0000

Data Index: 1253029 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.4300. Min Act: -0.0000

Data Index: 618975 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.2622. Min Act: -0.0000

Data Index: 1592835 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.4698. Min Act: -0.0000

Data Index: 850399 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.0558. Min Act: -0.0000

Data Index: 1659220 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 3.7952. Min Range: -3.7952

Max Act: 2.9936. Min Act: -0.0000

Data Index: 645143 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.3619. Min Act: -0.0000

Data Index: 1670854 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.3102. Min Act: -0.0000

Data Index: 1864882 (The Pile)

Max Activating Token Index: 782

Text #12

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.2136. Min Act: -0.0000

Data Index: 1608662 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.1287. Min Act: -0.0000

Data Index: 1145994 (The Pile)

Max Activating Token Index: 699

Text #14

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.3735. Min Act: -0.0000

Data Index: 1004551 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.2790. Min Act: -0.0000

Data Index: 769256 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.2521. Min Act: -0.0000

Data Index: 1981338 (The Pile)

Max Activating Token Index: 326

Text #17

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.1675. Min Act: -0.0000

Data Index: 400478 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 3.7952. Min Range: -3.7952

Max Act: 2.8932. Min Act: -0.0000

Data Index: 499145 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 3.7952. Min Range: -3.7952

Max Act: 3.2003. Min Act: -0.0000

Data Index: 952364 (The Pile)

Max Activating Token Index: 395