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

Dataset: The Pile

Neuron 3234 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.8684. Min Act: -0.0000

Data Index: 536917 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.9772. Min Act: -0.0000

Data Index: 1696720 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.8854. Min Act: -0.0000

Data Index: 1265792 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.8985. Min Act: -0.0000

Data Index: 764971 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.7183. Min Act: -0.0000

Data Index: 1315605 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.6009. Min Act: -0.0000

Data Index: 1042917 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.8109. Min Act: -0.0000

Data Index: 79654 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.7168. Min Act: -0.0000

Data Index: 1448077 (The Pile)

Max Activating Token Index: 491

Text #8

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.7312. Min Act: -0.0000

Data Index: 1473560 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.4536. Min Act: -0.0000

Data Index: 261680 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.1398. Min Act: -0.0000

Data Index: 218078 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.4406. Min Act: -0.0000

Data Index: 885318 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 5.9772. Min Range: -5.9772

Max Act: 4.3615. Min Act: -0.0000

Data Index: 217021 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.2045. Min Act: -0.0000

Data Index: 461525 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.2218. Min Act: -0.0000

Data Index: 1029761 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.3978. Min Act: -0.0000

Data Index: 188199 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.2238. Min Act: -0.0000

Data Index: 1145880 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 5.9772. Min Range: -5.9772

Max Act: 4.5873. Min Act: -0.0000

Data Index: 1951473 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 5.9772. Min Range: -5.9772

Max Act: 5.0444. Min Act: -0.0000

Data Index: 1718582 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 5.9772. Min Range: -5.9772

Max Act: 4.8648. Min Act: -0.0000

Data Index: 322375 (The Pile)

Max Activating Token Index: 349