Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 707 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7756. Min Act: -0.0002

Data Index: 581155 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6235. Min Act: -0.0003

Data Index: 103616 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5790. Min Act: -0.0002

Data Index: 833007 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5949. Min Act: -0.0003

Data Index: 568799 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5243. Min Act: -0.0003

Data Index: 674559 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4771. Min Act: -0.0002

Data Index: 25104 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5127. Min Act: -0.0003

Data Index: 860978 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4938. Min Act: -0.0003

Data Index: 501300 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4684. Min Act: -0.0002

Data Index: 823822 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4641. Min Act: -0.0002

Data Index: 989039 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4638. Min Act: -0.0003

Data Index: 148377 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4583. Min Act: -0.0002

Data Index: 674330 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4843. Min Act: -0.0002

Data Index: 850338 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4835. Min Act: -0.0003

Data Index: 364993 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4563. Min Act: -0.0002

Data Index: 371703 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4172. Min Act: -0.0003

Data Index: 967398 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.3756. Min Act: -0.0002

Data Index: 1102631 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.3718. Min Act: -0.0002

Data Index: 940499 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4312. Min Act: -0.0003

Data Index: 679893 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.4278. Min Act: -0.0003

Data Index: 328157 (C4 (Web Text))

Max Activating Token Index: 374