Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 715 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1133952 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0578. Min Act: -0.0002

Data Index: 274737 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0573. Min Act: -0.0002

Data Index: 614665 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0559. Min Act: -0.0003

Data Index: 730633 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0548. Min Act: -0.0003

Data Index: 680147 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1104846 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0543. Min Act: -0.0003

Data Index: 887010 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0539. Min Act: -0.0003

Data Index: 606940 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0541. Min Act: -0.0002

Data Index: 435632 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0526. Min Act: -0.0003

Data Index: 674210 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1332033 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1192655 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1280771 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0522. Min Act: -0.0002

Data Index: 108237 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0526. Min Act: -0.0002

Data Index: 358670 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0517. Min Act: -0.0003

Data Index: 873541 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0519. Min Act: -0.0003

Data Index: 607488 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1235123 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0518. Min Act: -0.0003

Data Index: 29579 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0523. Min Act: -0.0003

Data Index: 619363 (C4 (Web Text))

Max Activating Token Index: 197