Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1807 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1225040 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0550. Min Act: -0.0003

Data Index: 786442 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0541. Min Act: -0.0003

Data Index: 502090 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0533. Min Act: -0.0003

Data Index: 279558 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0545. Min Act: -0.0003

Data Index: 290714 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0530. Min Act: -0.0004

Data Index: 1050452 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0546. Min Act: -0.0004

Data Index: 1294759 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0529. Min Act: -0.0004

Data Index: 446951 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0524. Min Act: -0.0004

Data Index: 98879 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0522. Min Act: -0.0004

Data Index: 1230805 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0538. Min Act: -0.0004

Data Index: 667995 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0512. Min Act: -0.0003

Data Index: 103634 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0516. Min Act: -0.0002

Data Index: 830236 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1336064 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1320681 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0511. Min Act: -0.0004

Data Index: 1330569 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0507. Min Act: -0.0003

Data Index: 343351 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0506. Min Act: -0.0003

Data Index: 945408 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0498. Min Act: -0.0003

Data Index: 230324 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0503. Min Act: -0.0003

Data Index: 140681 (C4 (Web Text))

Max Activating Token Index: 314