Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3183 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0003

Data Index: 415081 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0496. Min Act: -0.0003

Data Index: 965351 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0537. Min Act: -0.0003

Data Index: 794997 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0517. Min Act: -0.0003

Data Index: 364562 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0452. Min Act: -0.0003

Data Index: 130162 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0459. Min Act: -0.0003

Data Index: 468241 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0496. Min Act: -0.0003

Data Index: 975177 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0483. Min Act: -0.0003

Data Index: 129860 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0508. Min Act: -0.0003

Data Index: 256489 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0488. Min Act: -0.0003

Data Index: 573424 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1140115 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0478. Min Act: -0.0003

Data Index: 510054 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0419. Min Act: -0.0003

Data Index: 146062 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1008012 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0405. Min Act: -0.0003

Data Index: 73090 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1003746 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0461. Min Act: -0.0003

Data Index: 937698 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0440. Min Act: -0.0003

Data Index: 674947 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1140319 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1027541 (C4 (Web Text))

Max Activating Token Index: 331