Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2469 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2553. Min Range: -1.2553

Max Act: 1.2553. Min Act: -0.0000

Data Index: 1447628 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 1.2553. Min Range: -1.2553

Max Act: 1.1203. Min Act: -0.0000

Data Index: 1562397 (Python Code)

Max Activating Token Index: 857

Text #2

Max Range: 1.2553. Min Range: -1.2553

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1652637 (Python Code)

Max Activating Token Index: 561

Text #3

Max Range: 1.2553. Min Range: -1.2553

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1579704 (Python Code)

Max Activating Token Index: 790

Text #4

Max Range: 1.2553. Min Range: -1.2553

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1519275 (Python Code)

Max Activating Token Index: 617

Text #5

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1505673 (Python Code)

Max Activating Token Index: 631

Text #6

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1644132 (Python Code)

Max Activating Token Index: 593

Text #7

Max Range: 1.2553. Min Range: -1.2553

Max Act: 1.0282. Min Act: -0.0000

Data Index: 1540482 (Python Code)

Max Activating Token Index: 794

Text #8

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1561100 (Python Code)

Max Activating Token Index: 446

Text #9

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.8609. Min Act: -0.0000

Data Index: 1505114 (Python Code)

Max Activating Token Index: 747

Text #10

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1539867 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1625406 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1606632 (Python Code)

Max Activating Token Index: 262

Text #13

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1375395 (Python Code)

Max Activating Token Index: 230

Text #14

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1600331 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1406507 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1364112 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1423754 (Python Code)

Max Activating Token Index: 77

Text #18

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1467675 (Python Code)

Max Activating Token Index: 736

Text #19

Max Range: 1.2553. Min Range: -1.2553

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1399155 (Python Code)

Max Activating Token Index: 951