Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4729 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0732. Min Act: -0.0003

Data Index: 987225 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0711. Min Act: -0.0002

Data Index: 662342 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0682. Min Act: -0.0003

Data Index: 632982 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0641. Min Act: -0.0003

Data Index: 312267 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1184139 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1489338 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0547. Min Act: -0.0002

Data Index: 810389 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0554. Min Act: -0.0003

Data Index: 801155 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0529. Min Act: -0.0003

Data Index: 146538 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0515. Min Act: -0.0003

Data Index: 504022 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1399842 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0524. Min Act: -0.0003

Data Index: 270857 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1583215 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1151554 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1316640 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1448267 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0475. Min Act: -0.0003

Data Index: 133538 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1412803 (Python Code)

Max Activating Token Index: 844

Text #18

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1370113 (Python Code)

Max Activating Token Index: 673

Text #19

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1637501 (Python Code)

Max Activating Token Index: 103