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

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

Neuron 936 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0510. Min Act: -0.0005

Data Index: 539255 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0005

Data Index: 798727 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0491. Min Act: -0.0005

Data Index: 887140 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0480. Min Act: -0.0005

Data Index: 1656279 (Python Code)

Max Activating Token Index: 490

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0467. Min Act: -0.0005

Data Index: 1443090 (Python Code)

Max Activating Token Index: 492

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0459. Min Act: -0.0005

Data Index: 553155 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0431. Min Act: -0.0005

Data Index: 565486 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0418. Min Act: -0.0005

Data Index: 224005 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0429. Min Act: -0.0005

Data Index: 1543337 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0431. Min Act: -0.0005

Data Index: 675549 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0417. Min Act: -0.0005

Data Index: 740155 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0440. Min Act: -0.0005

Data Index: 34867 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0422. Min Act: -0.0005

Data Index: 331509 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0403. Min Act: -0.0005

Data Index: 1581691 (Python Code)

Max Activating Token Index: 457

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0421. Min Act: -0.0005

Data Index: 1632239 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0413. Min Act: -0.0005

Data Index: 1425751 (Python Code)

Max Activating Token Index: 811

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0417. Min Act: -0.0005

Data Index: 1252036 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0379. Min Act: -0.0005

Data Index: 201024 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0386. Min Act: -0.0005

Data Index: 122787 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0389. Min Act: -0.0005

Data Index: 981478 (C4 (Web Text))

Max Activating Token Index: 462