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

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

Neuron 4458 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0732. Min Act: -0.0000

Data Index: 369058 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0673. Min Act: -0.0000

Data Index: 741444 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1328792 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1065432 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0508. Min Act: -0.0000

Data Index: 368055 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0515. Min Act: -0.0001

Data Index: 82116 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0448. Min Act: -0.0000

Data Index: 422295 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0516. Min Act: -0.0000

Data Index: 751106 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0448. Min Act: -0.0000

Data Index: 1591794 (Python Code)

Max Activating Token Index: 784

Text #9

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0504. Min Act: -0.0000

Data Index: 415880 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0490. Min Act: -0.0000

Data Index: 347214 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0473. Min Act: -0.0001

Data Index: 202355 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0424. Min Act: -0.0000

Data Index: 875399 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0454. Min Act: -0.0001

Data Index: 427562 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0402. Min Act: -0.0001

Data Index: 199723 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0463. Min Act: -0.0000

Data Index: 497581 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0461. Min Act: -0.0001

Data Index: 265525 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0436. Min Act: -0.0000

Data Index: 790128 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0419. Min Act: -0.0000

Data Index: 1015014 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0386. Min Act: -0.0000

Data Index: 959213 (C4 (Web Text))

Max Activating Token Index: 436