Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2005 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1669. Min Act: -0.0001

Data Index: 401829 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1628. Min Act: -0.0001

Data Index: 617685 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1643. Min Act: -0.0001

Data Index: 753234 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1608. Min Act: -0.0001

Data Index: 820131 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1553. Min Act: -0.0001

Data Index: 89315 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1331182 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1562. Min Act: -0.0001

Data Index: 900361 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1501. Min Act: -0.0001

Data Index: 357396 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1470. Min Act: -0.0001

Data Index: 278013 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1488. Min Act: -0.0001

Data Index: 921116 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1308560 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1289740 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1500. Min Act: -0.0001

Data Index: 832419 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1454. Min Act: -0.0001

Data Index: 726465 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1354487 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1415. Min Act: -0.0001

Data Index: 219087 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1334. Min Act: -0.0001

Data Index: 483953 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1378. Min Act: -0.0001

Data Index: 959993 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1424. Min Act: -0.0001

Data Index: 951095 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1333. Min Act: -0.0001

Data Index: 341696 (C4 (Web Text))

Max Activating Token Index: 139