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

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

Neuron 1937 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: 0.0542. Min Range: -0.0542

Max Act: 0.0502. Min Act: -0.0003

Data Index: 297463 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0511. Min Act: -0.0003

Data Index: 757647 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0517. Min Act: -0.0003

Data Index: 544806 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1139041 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0436. Min Act: -0.0003

Data Index: 221227 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0474. Min Act: -0.0003

Data Index: 264882 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0437. Min Act: -0.0003

Data Index: 985111 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0542. Min Act: -0.0003

Data Index: 428674 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0453. Min Act: -0.0003

Data Index: 65136 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0432. Min Act: -0.0003

Data Index: 915698 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0412. Min Act: -0.0003

Data Index: 734517 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0384. Min Act: -0.0003

Data Index: 774392 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0435. Min Act: -0.0003

Data Index: 24806 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1227160 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0416. Min Act: -0.0003

Data Index: 938676 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0373. Min Act: -0.0003

Data Index: 85651 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0370. Min Act: -0.0003

Data Index: 37360 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0382. Min Act: -0.0003

Data Index: 443021 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0422. Min Act: -0.0003

Data Index: 1045713 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0391. Min Act: -0.0003

Data Index: 484430 (C4 (Web Text))

Max Activating Token Index: 591