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

Dataset: The Pile

Neuron 2720 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.8605. Min Act: -0.0000

Data Index: 298229 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.5455. Min Act: -0.0000

Data Index: 1973298 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.6702. Min Act: -0.0000

Data Index: 1814867 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.5726. Min Act: -0.0000

Data Index: 1687488 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.4981. Min Act: -0.0000

Data Index: 803417 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.4777. Min Act: -0.0000

Data Index: 1987550 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.2761. Min Act: -0.0000

Data Index: 1525131 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.4024. Min Act: -0.0000

Data Index: 711468 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.1578. Min Act: -0.0000

Data Index: 352502 (The Pile)

Max Activating Token Index: 18

Text #9

Max Range: 3.8605. Min Range: -3.8605

Max Act: 2.9751. Min Act: -0.0000

Data Index: 1703314 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.2279. Min Act: -0.0000

Data Index: 413825 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 3.8605. Min Range: -3.8605

Max Act: 3.1596. Min Act: -0.0000

Data Index: 1922214 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 3.8605. Min Range: -3.8605

Max Act: 2.8315. Min Act: -0.0000

Data Index: 1390824 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 3.8605. Min Range: -3.8605

Max Act: 2.8313. Min Act: -0.0000

Data Index: 677474 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 3.8605. Min Range: -3.8605

Max Act: 2.9262. Min Act: -0.0000

Data Index: 1861657 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 3.8605. Min Range: -3.8605

Max Act: 2.7535. Min Act: -0.0000

Data Index: 748417 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 3.8605. Min Range: -3.8605

Max Act: 2.8963. Min Act: -0.0000

Data Index: 943253 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 3.8605. Min Range: -3.8605

Max Act: 2.8754. Min Act: -0.0000

Data Index: 839306 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 3.8605. Min Range: -3.8605

Max Act: 2.9678. Min Act: -0.0000

Data Index: 704796 (The Pile)

Max Activating Token Index: 187

Text #19

Max Range: 3.8605. Min Range: -3.8605

Max Act: 2.4405. Min Act: -0.0000

Data Index: 1104205 (The Pile)

Max Activating Token Index: 616