Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 90 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0002

Data Index: 992001 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0542. Min Act: -0.0002

Data Index: 782701 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1059659 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0471. Min Act: -0.0002

Data Index: 738090 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1291844 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0474. Min Act: -0.0002

Data Index: 920242 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1040940 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1232255 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0435. Min Act: -0.0002

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0443. Min Act: -0.0002

Data Index: 912580 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1306961 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1143492 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1266696 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1085268 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0444. Min Act: -0.0002

Data Index: 641018 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0421. Min Act: -0.0002

Data Index: 563206 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0423. Min Act: -0.0002

Data Index: 997106 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0428. Min Act: -0.0001

Data Index: 426760 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0428. Min Act: -0.0002

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0412. Min Act: -0.0002

Data Index: 223244 (C4 (Web Text))

Max Activating Token Index: 425