Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2381 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.9427. Min Act: -0.0000

Data Index: 960769 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.8974. Min Act: -0.0000

Data Index: 624595 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.8721. Min Act: -0.0000

Data Index: 863702 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.8110. Min Act: -0.0000

Data Index: 149946 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7548. Min Act: -0.0000

Data Index: 54907 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.8574. Min Act: -0.0000

Data Index: 445852 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.8170. Min Act: -0.0000

Data Index: 854750 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.8161. Min Act: -0.0001

Data Index: 58299 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1240452 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.8358. Min Act: -0.0000

Data Index: 451000 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1263585 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7992. Min Act: -0.0000

Data Index: 810990 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7900. Min Act: -0.0000

Data Index: 555689 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7970. Min Act: -0.0000

Data Index: 650578 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7654. Min Act: -0.0001

Data Index: 667473 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7626. Min Act: -0.0000

Data Index: 495688 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7465. Min Act: -0.0001

Data Index: 996066 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7432. Min Act: -0.0000

Data Index: 925055 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1019626 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.9427. Min Range: -0.9427

Max Act: 0.7366. Min Act: -0.0001

Data Index: 46507 (C4 (Web Text))

Max Activating Token Index: 115