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

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

Neuron 638 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2350. Min Act: -0.0001

Data Index: 655105 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2236. Min Act: -0.0001

Data Index: 76664 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2075. Min Act: -0.0001

Data Index: 906064 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2208. Min Act: -0.0001

Data Index: 974644 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1287246 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1829. Min Act: -0.0001

Data Index: 626749 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1863. Min Act: -0.0001

Data Index: 911307 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1620. Min Act: -0.0001

Data Index: 312945 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1730. Min Act: -0.0001

Data Index: 479678 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1768. Min Act: -0.0001

Data Index: 331803 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1115917 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1107751 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1650. Min Act: -0.0001

Data Index: 296973 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1652. Min Act: -0.0001

Data Index: 400486 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1644. Min Act: -0.0001

Data Index: 1003715 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1465. Min Act: -0.0001

Data Index: 422241 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1578. Min Act: -0.0001

Data Index: 939485 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1094225 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1573. Min Act: -0.0001

Data Index: 303458 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1523. Min Act: -0.0001

Data Index: 363581 (C4 (Web Text))

Max Activating Token Index: 919