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

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

Neuron 4231 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: 0.0656. Min Range: -0.0656

Max Act: 0.0656. Min Act: -0.0001

Data Index: 63229 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1530847 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0576. Min Act: -0.0001

Data Index: 388705 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0549. Min Act: -0.0001

Data Index: 903483 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1452148 (Python Code)

Max Activating Token Index: 104

Text #5

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0517. Min Act: -0.0001

Data Index: 154640 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0531. Min Act: -0.0001

Data Index: 685087 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0520. Min Act: -0.0002

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1060429 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0472. Min Act: -0.0001

Data Index: 49340 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0478. Min Act: -0.0001

Data Index: 599213 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0443. Min Act: -0.0002

Data Index: 7720 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0434. Min Act: -0.0001

Data Index: 166268 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1507444 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1413589 (Python Code)

Max Activating Token Index: 925

Text #15

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0398. Min Act: -0.0001

Data Index: 137166 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1213514 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1501836 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0413. Min Act: -0.0001

Data Index: 425241 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0397. Min Act: -0.0001

Data Index: 1180187 (C4 (Web Text))

Max Activating Token Index: 687