Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2030 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1122309 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0725. Min Act: -0.0003

Data Index: 71806 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0732. Min Act: -0.0003

Data Index: 944914 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0710. Min Act: -0.0003

Data Index: 577152 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0711. Min Act: -0.0003

Data Index: 2951 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0701. Min Act: -0.0003

Data Index: 525245 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0694. Min Act: -0.0004

Data Index: 1036080 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0656. Min Act: -0.0003

Data Index: 39117 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0667. Min Act: -0.0003

Data Index: 869969 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0677. Min Act: -0.0003

Data Index: 847742 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0653. Min Act: -0.0003

Data Index: 122479 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1185090 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0649. Min Act: -0.0003

Data Index: 296777 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0632. Min Act: -0.0003

Data Index: 585325 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1015431 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0653. Min Act: -0.0003

Data Index: 394362 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1170689 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0630. Min Act: -0.0003

Data Index: 610243 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0642. Min Act: -0.0004

Data Index: 803804 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1116726 (C4 (Web Text))

Max Activating Token Index: 798