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

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

Neuron 1583 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1739. Min Act: -0.0001

Data Index: 513536 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1827. Min Act: -0.0001

Data Index: 943206 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1757. Min Act: -0.0001

Data Index: 684018 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1509. Min Act: -0.0001

Data Index: 924659 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1240692 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1234. Min Act: -0.0001

Data Index: 131762 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1418. Min Act: -0.0001

Data Index: 112438 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1579. Min Act: -0.0001

Data Index: 761762 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1507. Min Act: -0.0001

Data Index: 387285 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1506. Min Act: -0.0001

Data Index: 835584 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1475. Min Act: -0.0001

Data Index: 67614 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1159460 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1129793 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1362. Min Act: -0.0001

Data Index: 191172 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1541. Min Act: -0.0001

Data Index: 616077 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1375. Min Act: -0.0001

Data Index: 291341 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1127525 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1069493 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1474. Min Act: -0.0001

Data Index: 761150 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1138067 (C4 (Web Text))

Max Activating Token Index: 209