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

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

Neuron 4403 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3392. Min Act: -0.0001

Data Index: 678823 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3188. Min Act: -0.0001

Data Index: 136718 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3142. Min Act: -0.0001

Data Index: 164850 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2979. Min Act: -0.0001

Data Index: 677470 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3021. Min Act: -0.0001

Data Index: 70444 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2933. Min Act: -0.0001

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2892. Min Act: -0.0001

Data Index: 961421 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2699. Min Act: -0.0001

Data Index: 76095 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2936. Min Act: -0.0001

Data Index: 873563 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2908. Min Act: -0.0001

Data Index: 448185 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2747. Min Act: -0.0001

Data Index: 363609 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2727. Min Act: -0.0001

Data Index: 777140 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2704. Min Act: -0.0001

Data Index: 802540 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2609. Min Act: -0.0001

Data Index: 148369 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2494. Min Act: -0.0001

Data Index: 1328370 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2468. Min Act: -0.0001

Data Index: 916624 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2398. Min Act: -0.0001

Data Index: 1270539 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2441. Min Act: -0.0001

Data Index: 128042 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2415. Min Act: -0.0001

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2349. Min Act: -0.0001

Data Index: 215307 (C4 (Web Text))

Max Activating Token Index: 333