Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 46 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.3004. Min Act: -0.0001

Data Index: 1637021 (Python Code)

Max Activating Token Index: 373

Text #1

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2895. Min Act: -0.0001

Data Index: 1436707 (Python Code)

Max Activating Token Index: 757

Text #2

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.3003. Min Act: -0.0000

Data Index: 244281 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2887. Min Act: -0.0001

Data Index: 1421814 (Python Code)

Max Activating Token Index: 604

Text #4

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2651. Min Act: -0.0001

Data Index: 1533921 (Python Code)

Max Activating Token Index: 765

Text #5

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2638. Min Act: -0.0001

Data Index: 1395115 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2696. Min Act: -0.0001

Data Index: 1604665 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2573. Min Act: -0.0001

Data Index: 1569387 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1434369 (Python Code)

Max Activating Token Index: 226

Text #9

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1609612 (Python Code)

Max Activating Token Index: 708

Text #10

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2482. Min Act: -0.0001

Data Index: 1483714 (Python Code)

Max Activating Token Index: 568

Text #11

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2484. Min Act: -0.0000

Data Index: 573641 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2455. Min Act: -0.0000

Data Index: 636810 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2426. Min Act: -0.0001

Data Index: 1468219 (Python Code)

Max Activating Token Index: 59

Text #14

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2415. Min Act: -0.0001

Data Index: 458723 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1584466 (Python Code)

Max Activating Token Index: 360

Text #16

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1592535 (Python Code)

Max Activating Token Index: 458

Text #17

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2410. Min Act: -0.0001

Data Index: 1291158 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2318. Min Act: -0.0001

Data Index: 1609102 (Python Code)

Max Activating Token Index: 850

Text #19

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2206. Min Act: -0.0001

Data Index: 1538629 (Python Code)

Max Activating Token Index: 830