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

Dataset: The Pile

Neuron 1710 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2633. Min Act: -0.0000

Data Index: 595253 (The Pile)

Max Activating Token Index: 181

Text #1

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1798204 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1267482 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2384. Min Act: -0.0000

Data Index: 471625 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2431. Min Act: -0.0000

Data Index: 460646 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2465. Min Act: -0.0000

Data Index: 778658 (The Pile)

Max Activating Token Index: 943

Text #6

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2340. Min Act: -0.0000

Data Index: 106856 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2221. Min Act: -0.0000

Data Index: 37381 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2287. Min Act: -0.0000

Data Index: 96920 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1527305 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1491667 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2143. Min Act: -0.0000

Data Index: 459445 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2351. Min Act: -0.0000

Data Index: 775223 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2170. Min Act: -0.0000

Data Index: 926475 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2476. Min Act: -0.0000

Data Index: 505783 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1073712 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1281392 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2244. Min Act: -0.0000

Data Index: 769250 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2073. Min Act: -0.0000

Data Index: 929631 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2226. Min Act: -0.0000

Data Index: 73823 (The Pile)

Max Activating Token Index: 239