Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 104 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1285099 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0498. Min Act: -0.0002

Data Index: 794361 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0482. Min Act: -0.0002

Data Index: 846878 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0492. Min Act: -0.0002

Data Index: 688301 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0478. Min Act: -0.0002

Data Index: 964201 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0483. Min Act: -0.0002

Data Index: 115786 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0477. Min Act: -0.0002

Data Index: 563056 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0482. Min Act: -0.0002

Data Index: 711062 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1332156 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0479. Min Act: -0.0002

Data Index: 135689 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1178389 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0485. Min Act: -0.0002

Data Index: 283800 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1132684 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0463. Min Act: -0.0002

Data Index: 164160 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0467. Min Act: -0.0002

Data Index: 610506 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0479. Min Act: -0.0002

Data Index: 679995 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0460. Min Act: -0.0002

Data Index: 130707 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0460. Min Act: -0.0002

Data Index: 923088 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0453. Min Act: -0.0002

Data Index: 132664 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0451. Min Act: -0.0002

Data Index: 161106 (C4 (Web Text))

Max Activating Token Index: 155