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

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

Neuron 2304 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: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0002

Data Index: 155366 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0572. Min Act: -0.0002

Data Index: 310467 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1303811 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1097770 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0500. Min Act: -0.0002

Data Index: 627073 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1152385 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0435. Min Act: -0.0002

Data Index: 532355 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0508. Min Act: -0.0002

Data Index: 39323 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1503422 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0520. Min Act: -0.0002

Data Index: 582836 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0484. Min Act: -0.0002

Data Index: 499777 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0550. Min Act: -0.0002

Data Index: 415842 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1251571 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1286181 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0480. Min Act: -0.0002

Data Index: 371682 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0482. Min Act: -0.0002

Data Index: 610242 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0452. Min Act: -0.0002

Data Index: 430198 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0473. Min Act: -0.0002

Data Index: 843323 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0474. Min Act: -0.0002

Data Index: 251601 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1552310 (Python Code)

Max Activating Token Index: 267