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

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

Neuron 610 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0006

Data Index: 173440 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0687. Min Act: -0.0006

Data Index: 292137 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0706. Min Act: -0.0006

Data Index: 823960 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0730. Min Act: -0.0005

Data Index: 299423 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0695. Min Act: -0.0006

Data Index: 48096 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0689. Min Act: -0.0006

Data Index: 388620 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0676. Min Act: -0.0006

Data Index: 560557 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0667. Min Act: -0.0006

Data Index: 780323 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0664. Min Act: -0.0006

Data Index: 980133 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0634. Min Act: -0.0006

Data Index: 994465 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0659. Min Act: -0.0006

Data Index: 1344150 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0674. Min Act: -0.0006

Data Index: 199393 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0639. Min Act: -0.0006

Data Index: 1222321 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0635. Min Act: -0.0006

Data Index: 1205289 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0632. Min Act: -0.0006

Data Index: 1354971 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0605. Min Act: -0.0005

Data Index: 396 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0629. Min Act: -0.0006

Data Index: 994671 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0643. Min Act: -0.0005

Data Index: 578798 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0591. Min Act: -0.0006

Data Index: 101205 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0581. Min Act: -0.0005

Data Index: 1221944 (C4 (Web Text))

Max Activating Token Index: 759