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

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

Neuron 4070 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5533. Min Act: -0.0001

Data Index: 939046 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4131. Min Act: -0.0001

Data Index: 1352696 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3726. Min Act: -0.0001

Data Index: 399015 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1026126 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3234. Min Act: -0.0001

Data Index: 423282 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3167. Min Act: -0.0001

Data Index: 894862 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3083. Min Act: -0.0001

Data Index: 93757 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3054. Min Act: -0.0001

Data Index: 471559 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2648. Min Act: -0.0001

Data Index: 54427 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2743. Min Act: -0.0001

Data Index: 10165 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2771. Min Act: -0.0001

Data Index: 878524 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2892. Min Act: -0.0001

Data Index: 471387 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2499. Min Act: -0.0001

Data Index: 524464 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2910. Min Act: -0.0001

Data Index: 330194 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1301499 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2585. Min Act: -0.0001

Data Index: 1038055 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2812. Min Act: -0.0001

Data Index: 859995 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2859. Min Act: -0.0001

Data Index: 138047 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1122297 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2843. Min Act: -0.0001

Data Index: 855356 (C4 (Web Text))

Max Activating Token Index: 488