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

Dataset: The Pile

Neuron 3372 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: 3.5444. Min Range: -3.5444

Max Act: 3.5444. Min Act: -0.0000

Data Index: 896656 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.5386. Min Act: -0.0000

Data Index: 171948 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.5101. Min Act: -0.0000

Data Index: 1073479 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2474. Min Act: -0.0000

Data Index: 411019 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2144. Min Act: -0.0000

Data Index: 741619 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2495. Min Act: -0.0000

Data Index: 933103 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.0338. Min Act: -0.0000

Data Index: 1970798 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.8723. Min Act: -0.0000

Data Index: 1983259 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.9272. Min Act: -0.0000

Data Index: 943162 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.9702. Min Act: -0.0000

Data Index: 1505354 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.8672. Min Act: -0.0000

Data Index: 1057685 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.0716. Min Act: -0.0000

Data Index: 1799158 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.5994. Min Act: -0.0000

Data Index: 1747550 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.5408. Min Act: -0.0000

Data Index: 1932701 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.6192. Min Act: -0.0000

Data Index: 1624815 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.7583. Min Act: -0.0000

Data Index: 462203 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.8228. Min Act: -0.0000

Data Index: 717160 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.6330. Min Act: -0.0000

Data Index: 669303 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.5893. Min Act: -0.0000

Data Index: 543339 (The Pile)

Max Activating Token Index: 587

Text #19

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.4368. Min Act: -0.0000

Data Index: 649118 (The Pile)

Max Activating Token Index: 618