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

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

Neuron 595 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: 0.1981. Min Range: -0.1981

Max Act: 0.1946. Min Act: -0.0003

Data Index: 1091594 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1981. Min Act: -0.0003

Data Index: 568483 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1898. Min Act: -0.0003

Data Index: 651430 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1620. Min Act: -0.0003

Data Index: 1089823 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1743. Min Act: -0.0003

Data Index: 692794 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1809. Min Act: -0.0003

Data Index: 359119 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1633. Min Act: -0.0003

Data Index: 1332205 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1679. Min Act: -0.0003

Data Index: 470796 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1676. Min Act: -0.0003

Data Index: 122013 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1538. Min Act: -0.0003

Data Index: 314884 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1578. Min Act: -0.0003

Data Index: 43642 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1546. Min Act: -0.0003

Data Index: 435689 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1531. Min Act: -0.0003

Data Index: 1190545 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1559. Min Act: -0.0003

Data Index: 836921 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1452. Min Act: -0.0003

Data Index: 740783 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1465. Min Act: -0.0003

Data Index: 1353281 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1344. Min Act: -0.0003

Data Index: 222546 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1502. Min Act: -0.0003

Data Index: 702524 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1506. Min Act: -0.0003

Data Index: 734590 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1545. Min Act: -0.0003

Data Index: 1042821 (C4 (Web Text))

Max Activating Token Index: 212