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

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

Neuron 4866 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.5649. Min Act: -0.0000

Data Index: 28423 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.5192. Min Act: -0.0000

Data Index: 1459410 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.5184. Min Act: -0.0000

Data Index: 1236498 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.3432. Min Act: -0.0000

Data Index: 159918 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1479630 (Python Code)

Max Activating Token Index: 891

Text #5

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.3284. Min Act: -0.0000

Data Index: 43023 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.2808. Min Act: -0.0000

Data Index: 594430 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1094005 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1332710 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1432519 (Python Code)

Max Activating Token Index: 612

Text #10

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1504279 (Python Code)

Max Activating Token Index: 345

Text #11

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1647993 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.2803. Min Act: -0.0000

Data Index: 504617 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.1644. Min Act: -0.0000

Data Index: 1517240 (Python Code)

Max Activating Token Index: 801

Text #14

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.1462. Min Act: -0.0000

Data Index: 630847 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1429627 (Python Code)

Max Activating Token Index: 1016

Text #16

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.2227. Min Act: -0.0000

Data Index: 1071407 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.1359. Min Act: -0.0000

Data Index: 838729 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.0915. Min Act: -0.0000

Data Index: 569522 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 1.5649. Min Range: -1.5649

Max Act: 1.1324. Min Act: -0.0000

Data Index: 1585021 (Python Code)

Max Activating Token Index: 22