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

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

Neuron 1795 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: 0.0720. Min Range: -0.0720

Max Act: 0.0720. Min Act: -0.0003

Data Index: 714324 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1059442 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0647. Min Act: -0.0003

Data Index: 287161 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0539. Min Act: -0.0003

Data Index: 587825 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1072275 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0498. Min Act: -0.0003

Data Index: 89058 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0497. Min Act: -0.0003

Data Index: 501054 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0465. Min Act: -0.0003

Data Index: 572623 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0450. Min Act: -0.0003

Data Index: 680793 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0416. Min Act: -0.0003

Data Index: 847084 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0480. Min Act: -0.0003

Data Index: 616289 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0463. Min Act: -0.0003

Data Index: 953700 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0482. Min Act: -0.0003

Data Index: 570972 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0441. Min Act: -0.0003

Data Index: 71271 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1336943 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0415. Min Act: -0.0003

Data Index: 242679 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1283652 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0443. Min Act: -0.0003

Data Index: 669558 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1184852 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0392. Min Act: -0.0003

Data Index: 393860 (C4 (Web Text))

Max Activating Token Index: 552