Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3618 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3820. Min Act: -0.0002

Data Index: 1307433 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3124. Min Act: -0.0001

Data Index: 788816 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3357. Min Act: -0.0001

Data Index: 561342 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2725. Min Act: -0.0001

Data Index: 645035 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2751. Min Act: -0.0001

Data Index: 196779 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2724. Min Act: -0.0001

Data Index: 590927 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2782. Min Act: -0.0001

Data Index: 1060960 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2509. Min Act: -0.0001

Data Index: 713542 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2523. Min Act: -0.0001

Data Index: 639250 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2621. Min Act: -0.0001

Data Index: 933809 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2838. Min Act: -0.0001

Data Index: 246505 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2691. Min Act: -0.0001

Data Index: 692110 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2367. Min Act: -0.0001

Data Index: 665621 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2898. Min Act: -0.0001

Data Index: 1643089 (Python Code)

Max Activating Token Index: 248

Text #14

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2607. Min Act: -0.0001

Data Index: 493204 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2498. Min Act: -0.0001

Data Index: 784415 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2392. Min Act: -0.0001

Data Index: 271682 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2586. Min Act: -0.0001

Data Index: 43542 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2704. Min Act: -0.0001

Data Index: 1154620 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2019. Min Act: -0.0001

Data Index: 524966 (C4 (Web Text))

Max Activating Token Index: 218