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

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

Neuron 4555 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0003

Data Index: 689088 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0628. Min Act: -0.0002

Data Index: 391831 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0563. Min Act: -0.0002

Data Index: 73361 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0560. Min Act: -0.0003

Data Index: 365325 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0543. Min Act: -0.0003

Data Index: 361084 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0541. Min Act: -0.0003

Data Index: 906852 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0536. Min Act: -0.0002

Data Index: 476939 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0518. Min Act: -0.0002

Data Index: 931679 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0517. Min Act: -0.0002

Data Index: 287215 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1146009 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0490. Min Act: -0.0003

Data Index: 893018 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1330599 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0462. Min Act: -0.0002

Data Index: 84948 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0464. Min Act: -0.0002

Data Index: 723142 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0450. Min Act: -0.0002

Data Index: 772046 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0459. Min Act: -0.0002

Data Index: 125930 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1210257 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1058521 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0445. Min Act: -0.0002

Data Index: 682397 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1034049 (C4 (Web Text))

Max Activating Token Index: 492