Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1928 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1205415 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0520. Min Act: -0.0002

Data Index: 350243 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0508. Min Act: -0.0001

Data Index: 635843 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0529. Min Act: -0.0002

Data Index: 861559 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0491. Min Act: -0.0002

Data Index: 722631 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0469. Min Act: -0.0002

Data Index: 771835 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0421. Min Act: -0.0002

Data Index: 363170 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1058617 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0433. Min Act: -0.0002

Data Index: 434534 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0438. Min Act: -0.0002

Data Index: 156890 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0436. Min Act: -0.0002

Data Index: 986715 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1177037 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0436. Min Act: -0.0002

Data Index: 685149 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0425. Min Act: -0.0002

Data Index: 725235 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0455. Min Act: -0.0002

Data Index: 887268 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0426. Min Act: -0.0002

Data Index: 958744 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0418. Min Act: -0.0002

Data Index: 554197 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0422. Min Act: -0.0002

Data Index: 824332 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1218402 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0430. Min Act: -0.0001

Data Index: 843289 (C4 (Web Text))

Max Activating Token Index: 617