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

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

Neuron 3125 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 753388 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0711. Min Act: -0.0002

Data Index: 988441 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1200112 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0558. Min Act: -0.0002

Data Index: 416883 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0568. Min Act: -0.0002

Data Index: 169431 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0510. Min Act: -0.0002

Data Index: 391891 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0525. Min Act: -0.0002

Data Index: 921397 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0503. Min Act: -0.0002

Data Index: 472266 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1296504 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0492. Min Act: -0.0002

Data Index: 894314 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0493. Min Act: -0.0002

Data Index: 164128 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0465. Min Act: -0.0002

Data Index: 3734 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0465. Min Act: -0.0002

Data Index: 859373 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0532. Min Act: -0.0002

Data Index: 881190 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0440. Min Act: -0.0002

Data Index: 738802 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1081663 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0499. Min Act: -0.0002

Data Index: 224932 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1037180 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1304271 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0452. Min Act: -0.0002

Data Index: 463600 (C4 (Web Text))

Max Activating Token Index: 335