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

Dataset: The Pile

Neuron 4910 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4445. Min Range: -4.4445

Max Act: 4.4445. Min Act: -0.0000

Data Index: 1184212 (The Pile)

Max Activating Token Index: 261

Text #1

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.4491. Min Act: -0.0000

Data Index: 369355 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.5984. Min Act: -0.0000

Data Index: 299223 (The Pile)

Max Activating Token Index: 720

Text #3

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.8102. Min Act: -0.0000

Data Index: 493474 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.5815. Min Act: -0.0000

Data Index: 387707 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.7471. Min Act: -0.0000

Data Index: 1012022 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.5420. Min Act: -0.0000

Data Index: 1726518 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.5275. Min Act: -0.0000

Data Index: 345340 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.6565. Min Act: -0.0000

Data Index: 1813461 (The Pile)

Max Activating Token Index: 818

Text #9

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.6295. Min Act: -0.0000

Data Index: 1886578 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.4578. Min Act: -0.0000

Data Index: 442371 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.5821. Min Act: -0.0000

Data Index: 1381671 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.2636. Min Act: -0.0000

Data Index: 1016865 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.4038. Min Act: -0.0000

Data Index: 557194 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.4246. Min Act: -0.0000

Data Index: 833696 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.5419. Min Act: -0.0000

Data Index: 794916 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.7272. Min Act: -0.0000

Data Index: 964466 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.6619. Min Act: -0.0000

Data Index: 383245 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.6641. Min Act: -0.0000

Data Index: 1167243 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 4.4445. Min Range: -4.4445

Max Act: 3.4961. Min Act: -0.0000

Data Index: 1409769 (The Pile)

Max Activating Token Index: 424