Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1993 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0004

Data Index: 331207 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0610. Min Act: -0.0003

Data Index: 200735 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0563. Min Act: -0.0003

Data Index: 278111 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0527. Min Act: -0.0002

Data Index: 898792 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0556. Min Act: -0.0003

Data Index: 268385 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0548. Min Act: -0.0003

Data Index: 81688 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0498. Min Act: -0.0003

Data Index: 814857 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0540. Min Act: -0.0002

Data Index: 888617 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1358376 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0542. Min Act: -0.0003

Data Index: 95405 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0513. Min Act: -0.0003

Data Index: 683769 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1065074 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1161740 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0495. Min Act: -0.0003

Data Index: 935216 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0502. Min Act: -0.0003

Data Index: 394575 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0502. Min Act: -0.0003

Data Index: 707961 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0498. Min Act: -0.0003

Data Index: 166355 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1049229 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1310480 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0480. Min Act: -0.0003

Data Index: 946222 (C4 (Web Text))

Max Activating Token Index: 180