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

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

Neuron 871 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: 0.9622. Min Range: -0.9622

Max Act: 0.9622. Min Act: -0.0001

Data Index: 755089 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6939. Min Act: -0.0001

Data Index: 1121112 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6613. Min Act: -0.0001

Data Index: 1054835 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5661. Min Act: -0.0001

Data Index: 619804 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5981. Min Act: -0.0000

Data Index: 618792 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5541. Min Act: -0.0000

Data Index: 536465 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5343. Min Act: -0.0001

Data Index: 1226225 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5460. Min Act: -0.0001

Data Index: 85176 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5239. Min Act: -0.0001

Data Index: 200606 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5087. Min Act: -0.0001

Data Index: 695785 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5097. Min Act: -0.0001

Data Index: 485638 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5378. Min Act: -0.0001

Data Index: 316714 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1116528 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5256. Min Act: -0.0001

Data Index: 247116 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.4682. Min Act: -0.0001

Data Index: 595595 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5012. Min Act: -0.0000

Data Index: 673332 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5063. Min Act: -0.0000

Data Index: 474402 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.4784. Min Act: -0.0000

Data Index: 345328 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.4725. Min Act: -0.0001

Data Index: 531228 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.4764. Min Act: -0.0000

Data Index: 172783 (C4 (Web Text))

Max Activating Token Index: 753