Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5124 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0002

Data Index: 2971 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1144558 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0529. Min Act: -0.0002

Data Index: 657034 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1180979 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0509. Min Act: -0.0002

Data Index: 141734 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0502. Min Act: -0.0002

Data Index: 472702 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1341410 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0488. Min Act: -0.0002

Data Index: 333262 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0485. Min Act: -0.0002

Data Index: 939789 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0482. Min Act: -0.0002

Data Index: 461231 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0486. Min Act: -0.0002

Data Index: 187353 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0475. Min Act: -0.0002

Data Index: 198884 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0469. Min Act: -0.0002

Data Index: 438233 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1119047 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0476. Min Act: -0.0002

Data Index: 955708 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0481. Min Act: -0.0002

Data Index: 689246 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0472. Min Act: -0.0002

Data Index: 244675 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0473. Min Act: -0.0002

Data Index: 169940 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0463. Min Act: -0.0002

Data Index: 293524 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0472. Min Act: -0.0002

Data Index: 376427 (C4 (Web Text))

Max Activating Token Index: 742