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

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

Neuron 2787 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1779. Min Act: -0.0002

Data Index: 623726 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1789. Min Act: -0.0002

Data Index: 414224 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1773. Min Act: -0.0002

Data Index: 349526 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1747. Min Act: -0.0002

Data Index: 131092 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1671. Min Act: -0.0002

Data Index: 326053 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1617. Min Act: -0.0002

Data Index: 52128 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1593. Min Act: -0.0002

Data Index: 959775 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1626. Min Act: -0.0002

Data Index: 369272 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1503. Min Act: -0.0002

Data Index: 728161 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1461. Min Act: -0.0002

Data Index: 178700 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1448. Min Act: -0.0002

Data Index: 235162 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1446. Min Act: -0.0002

Data Index: 136266 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1423. Min Act: -0.0002

Data Index: 265640 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1412. Min Act: -0.0002

Data Index: 986280 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1336. Min Act: -0.0002

Data Index: 144587 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1390. Min Act: -0.0002

Data Index: 61264 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1382. Min Act: -0.0002

Data Index: 466747 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1385. Min Act: -0.0002

Data Index: 1242902 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1266683 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1352. Min Act: -0.0002

Data Index: 447596 (C4 (Web Text))

Max Activating Token Index: 392