Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 473 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0592. Min Act: -0.0002

Data Index: 679666 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0002

Data Index: 908362 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0548. Min Act: -0.0002

Data Index: 653817 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0552. Min Act: -0.0002

Data Index: 474727 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0537. Min Act: -0.0001

Data Index: 332197 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0540. Min Act: -0.0002

Data Index: 366820 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0536. Min Act: -0.0002

Data Index: 850444 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0545. Min Act: -0.0002

Data Index: 29629 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1174359 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0518. Min Act: -0.0002

Data Index: 861356 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0491. Min Act: -0.0002

Data Index: 761049 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0493. Min Act: -0.0002

Data Index: 862555 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0483. Min Act: -0.0002

Data Index: 235583 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0485. Min Act: -0.0002

Data Index: 90947 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0487. Min Act: -0.0002

Data Index: 280618 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0483. Min Act: -0.0002

Data Index: 758122 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0470. Min Act: -0.0002

Data Index: 658668 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0476. Min Act: -0.0002

Data Index: 625436 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0472. Min Act: -0.0002

Data Index: 212673 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1016544 (C4 (Web Text))

Max Activating Token Index: 850