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

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

Neuron 3061 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.3046. Min Act: -0.0002

Data Index: 446472 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.3075. Min Act: -0.0002

Data Index: 32008 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2741. Min Act: -0.0002

Data Index: 1061152 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2517. Min Act: -0.0002

Data Index: 447008 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2667. Min Act: -0.0002

Data Index: 428508 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2714. Min Act: -0.0002

Data Index: 350163 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2511. Min Act: -0.0002

Data Index: 422194 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2560. Min Act: -0.0002

Data Index: 136358 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2399. Min Act: -0.0002

Data Index: 561427 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2496. Min Act: -0.0002

Data Index: 1183945 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2404. Min Act: -0.0002

Data Index: 237787 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2368. Min Act: -0.0002

Data Index: 1354377 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2575. Min Act: -0.0002

Data Index: 956439 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2535. Min Act: -0.0002

Data Index: 1026011 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2592. Min Act: -0.0002

Data Index: 1167681 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2412. Min Act: -0.0002

Data Index: 769609 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2545. Min Act: -0.0002

Data Index: 1243057 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2534. Min Act: -0.0002

Data Index: 510101 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2309. Min Act: -0.0002

Data Index: 1218016 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2151. Min Act: -0.0002

Data Index: 387856 (C4 (Web Text))

Max Activating Token Index: 155