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

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

Neuron 3125 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0506. Min Act: -0.0001

Data Index: 939932 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0001

Data Index: 17101 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0492. Min Act: -0.0001

Data Index: 859716 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0600. Min Act: -0.0001

Data Index: 52935 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0594. Min Act: -0.0001

Data Index: 71226 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0597. Min Act: -0.0001

Data Index: 175910 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0513. Min Act: -0.0001

Data Index: 302516 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0562. Min Act: -0.0001

Data Index: 62575 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1296804 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0592. Min Act: -0.0001

Data Index: 639197 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0510. Min Act: -0.0001

Data Index: 791856 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0478. Min Act: -0.0001

Data Index: 819852 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0462. Min Act: -0.0001

Data Index: 859956 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0504. Min Act: -0.0001

Data Index: 961540 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0443. Min Act: -0.0001

Data Index: 159800 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0436. Min Act: -0.0001

Data Index: 615038 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1164551 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0466. Min Act: -0.0001

Data Index: 116901 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0453. Min Act: -0.0001

Data Index: 114078 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0481. Min Act: -0.0001

Data Index: 511188 (C4 (Web Text))

Max Activating Token Index: 974