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

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

Neuron 4299 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: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0001

Data Index: 368891 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0775. Min Act: -0.0001

Data Index: 183361 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1105946 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0805. Min Act: -0.0001

Data Index: 578147 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0756. Min Act: -0.0001

Data Index: 869353 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0790. Min Act: -0.0001

Data Index: 418178 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0675. Min Act: -0.0001

Data Index: 1169374 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1261608 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1144029 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0743. Min Act: -0.0001

Data Index: 532642 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1091363 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0616. Min Act: -0.0001

Data Index: 811821 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0611. Min Act: -0.0001

Data Index: 24206 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0631. Min Act: -0.0001

Data Index: 236576 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1327588 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0677. Min Act: -0.0001

Data Index: 854984 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0645. Min Act: -0.0001

Data Index: 504545 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0643. Min Act: -0.0001

Data Index: 287620 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0639. Min Act: -0.0001

Data Index: 356518 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0633. Min Act: -0.0001

Data Index: 381204 (C4 (Web Text))

Max Activating Token Index: 192