Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2234 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1744. Min Act: -0.0001

Data Index: 505832 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1246366 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1731. Min Act: -0.0001

Data Index: 531920 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1710. Min Act: -0.0001

Data Index: 615926 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1663. Min Act: -0.0001

Data Index: 797627 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1003651 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1741. Min Act: -0.0001

Data Index: 5939 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1021119 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1546. Min Act: -0.0001

Data Index: 530601 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1688. Min Act: -0.0001

Data Index: 506466 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1657. Min Act: -0.0001

Data Index: 532956 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1653. Min Act: -0.0001

Data Index: 105429 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1587. Min Act: -0.0001

Data Index: 452606 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1421. Min Act: -0.0001

Data Index: 614650 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1556. Min Act: -0.0001

Data Index: 868635 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1086759 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1287639 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1539. Min Act: -0.0001

Data Index: 911518 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1069841 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1003850 (C4 (Web Text))

Max Activating Token Index: 805