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

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

Neuron 1208 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: 0.0571. Min Range: -0.0571

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1067977 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0557. Min Act: -0.0003

Data Index: 964437 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1337656 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0481. Min Act: -0.0003

Data Index: 251161 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1153499 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0474. Min Act: -0.0003

Data Index: 776995 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0481. Min Act: -0.0004

Data Index: 561431 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0477. Min Act: -0.0003

Data Index: 521007 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0465. Min Act: -0.0004

Data Index: 835939 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1060689 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0485. Min Act: -0.0004

Data Index: 554122 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1251775 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0460. Min Act: -0.0003

Data Index: 37315 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1156399 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0444. Min Act: -0.0003

Data Index: 445684 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0443. Min Act: -0.0004

Data Index: 1129295 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0437. Min Act: -0.0003

Data Index: 684032 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0427. Min Act: -0.0003

Data Index: 972862 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1266749 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1312147 (C4 (Web Text))

Max Activating Token Index: 297