Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1415 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2847. Min Act: -0.0001

Data Index: 1073316 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2620. Min Act: -0.0001

Data Index: 72483 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2609. Min Act: -0.0001

Data Index: 517956 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2581. Min Act: -0.0001

Data Index: 621100 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2438. Min Act: -0.0001

Data Index: 759404 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2585. Min Act: -0.0001

Data Index: 493330 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2424. Min Act: -0.0001

Data Index: 18700 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2364. Min Act: -0.0001

Data Index: 843574 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2418. Min Act: -0.0001

Data Index: 867415 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1082783 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2674. Min Act: -0.0001

Data Index: 812278 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2553. Min Act: -0.0001

Data Index: 1184869 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2343. Min Act: -0.0001

Data Index: 1189611 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2423. Min Act: -0.0001

Data Index: 769469 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2586. Min Act: -0.0001

Data Index: 1348734 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2377. Min Act: -0.0001

Data Index: 115446 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2371. Min Act: -0.0001

Data Index: 657120 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1333647 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2677. Min Act: -0.0001

Data Index: 783846 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1076874 (C4 (Web Text))

Max Activating Token Index: 647