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

Dataset: The Pile

Neuron 41 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: 0.4675. Min Range: -0.4675

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1283361 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4528. Min Act: -0.0000

Data Index: 289956 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1026679 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1742469 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1708129 (The Pile)

Max Activating Token Index: 785

Text #5

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4118. Min Act: -0.0000

Data Index: 677397 (The Pile)

Max Activating Token Index: 888

Text #6

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1915393 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1733001 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3663. Min Act: -0.0000

Data Index: 602610 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1440349 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3528. Min Act: -0.0000

Data Index: 72407 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3510. Min Act: -0.0000

Data Index: 671540 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1042737 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3406. Min Act: -0.0000

Data Index: 250568 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1368694 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3257. Min Act: -0.0000

Data Index: 930300 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3362. Min Act: -0.0000

Data Index: 355536 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3228. Min Act: -0.0000

Data Index: 541098 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3556. Min Act: -0.0000

Data Index: 674690 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1105274 (The Pile)

Max Activating Token Index: 183