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

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

Neuron 1414 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0003

Data Index: 249016 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0543. Min Act: -0.0003

Data Index: 140537 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0546. Min Act: -0.0003

Data Index: 890245 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0538. Min Act: -0.0003

Data Index: 186559 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0547. Min Act: -0.0003

Data Index: 733534 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0538. Min Act: -0.0003

Data Index: 162006 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0484. Min Act: -0.0003

Data Index: 949755 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1046713 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0473. Min Act: -0.0003

Data Index: 93109 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1224559 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0513. Min Act: -0.0003

Data Index: 919783 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0448. Min Act: -0.0003

Data Index: 877462 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1211914 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0411. Min Act: -0.0003

Data Index: 253545 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0468. Min Act: -0.0003

Data Index: 408475 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1291186 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0430. Min Act: -0.0003

Data Index: 471126 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0419. Min Act: -0.0003

Data Index: 361052 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0401. Min Act: -0.0003

Data Index: 504593 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0444. Min Act: -0.0003

Data Index: 398624 (C4 (Web Text))

Max Activating Token Index: 843