Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2404 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1004818 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1530. Min Act: -0.0000

Data Index: 408740 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1671. Min Act: -0.0001

Data Index: 625619 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1109494 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1540. Min Act: -0.0000

Data Index: 986393 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1572. Min Act: -0.0001

Data Index: 413824 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1493. Min Act: -0.0000

Data Index: 492675 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1575. Min Act: -0.0001

Data Index: 430673 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1368. Min Act: -0.0001

Data Index: 148548 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1208075 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1393. Min Act: -0.0000

Data Index: 658221 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1139868 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1304. Min Act: -0.0001

Data Index: 436771 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1511. Min Act: -0.0000

Data Index: 138969 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1191. Min Act: -0.0001

Data Index: 929992 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1370. Min Act: -0.0000

Data Index: 369466 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1331. Min Act: -0.0001

Data Index: 441955 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1258. Min Act: -0.0000

Data Index: 67606 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1406. Min Act: -0.0000

Data Index: 390649 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1267. Min Act: -0.0001

Data Index: 89418 (C4 (Web Text))

Max Activating Token Index: 863