Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 301 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0767. Min Act: -0.0001

Data Index: 43500 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1020664 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0916. Min Act: -0.0001

Data Index: 833280 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0685. Min Act: -0.0001

Data Index: 457982 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1170715 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0481. Min Act: -0.0001

Data Index: 245375 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1256315 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0612. Min Act: -0.0001

Data Index: 765126 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0657. Min Act: -0.0001

Data Index: 645348 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0695. Min Act: -0.0001

Data Index: 453152 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0605. Min Act: -0.0001

Data Index: 853078 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1521559 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1301704 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1040622 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0685. Min Act: -0.0001

Data Index: 865465 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0531. Min Act: -0.0001

Data Index: 201280 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1127501 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0557. Min Act: -0.0001

Data Index: 571961 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0538. Min Act: -0.0001

Data Index: 989081 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0516. Min Act: -0.0001

Data Index: 876618 (C4 (Web Text))

Max Activating Token Index: 939