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

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

Neuron 1289 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1315662 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0442. Min Act: -0.0002

Data Index: 82622 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0515. Min Act: -0.0002

Data Index: 268670 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1306728 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0478. Min Act: -0.0002

Data Index: 434080 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1568459 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1184384 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0459. Min Act: -0.0002

Data Index: 785004 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1272427 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1138295 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0409. Min Act: -0.0002

Data Index: 877854 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0414. Min Act: -0.0002

Data Index: 160166 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1385383 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0373. Min Act: -0.0002

Data Index: 860977 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0378. Min Act: -0.0002

Data Index: 987226 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1318846 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0402. Min Act: -0.0002

Data Index: 634619 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1519486 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1169247 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1422308 (Python Code)

Max Activating Token Index: 482